Daniel: Hello everyone. Yeah, thanks so much for coming today. Much appreciated. Yes, I'm Daniel. I'm from Unsloth. My brother is also here today. But yeah, like you know, thanks for coming. So for you folks who don't know us, we actually, you know, we're one of the largest distributors of language models and diffusion models as well. So we don't just do language models. We upload our models to Hugging Face. And you know, we're on the... I think we're number 10 or something on the list of the top organizations on Hugging Face. We have over 300 million total downloads. So definitely check us out on that. You can run like you know DeepSeek, GLM, many other models and we quantize them down using dynamic quantization. So you can run them on your local computer.

Daniel: We also do many bug fixes for open source models. So you know we fix many bugs in OpenAI's GPUs, Meta's models, Google's models, DeepSeek, many other models we fix bugs in them. And so they have many issues sometimes and then we post about them on Twitter. You know we post about our findings. So most of the open source models that you guys have used are most likely fixed by us. And yeah, we collaborate with everyone in the entire world on model releases. We also collaborate with hardware providers and we really appreciate the collaborations with everyone. We also don't just do model fixes and bugs, we also introduce new features and we also do fixes for the entire training stack. For example, we introduced something called async gradient checkpointing which is used by many organizations. We also introduced flex attention which is used by many folks. And we also fixed a gradient accumulation bug fix which increased accuracy by 1 to 3% across the entire training stack. So we don't just do bug fixes for models, it's also whole training stack fixes and stuff like that.

Daniel: So today, the workshop is quite long. So there will be multiple sections in the workshop. And so after each section, anyone can ask a question. And so, please, I guess, if I'm not sure if there's a microphone, but if you could raise your voice and you ask a question, I'm more than happy to answer them. But the first section we're going to be talking about is the state of AI. So, where is currently language models, AI models, where are they at currently?

Daniel: So I'm not sure if everyone knows the meter plot. So this meter plot shows the time horizon of models. If every single task, if it takes a human 16 hours, can a model finish that task. And you can see on this plot, Claude Mythos preview is very good. It can do tasks that humans can do that take a human 16 hours. Opus 4.6 is also there. All the other models are also there. And so you know this plot is very good because it symbolizes the AI models are getting better and better and better over time. Recently with the launch of GPT-5.6 preview model just on Friday, I put the plot so they didn't actually update their plot because they said that the results were not trustworthy enough, but I just put it on the plot. And so you can see that GPT-5.6 is around Opus 4.6 level I guess with large confidence bounds. So it's very uncertain about the capabilities of the model. However, if you include cheating, so if you include that the model sometimes likes to cheat on some of the tasks, then it actually goes to 270 hours. So if you look at the y-axis I actually did a disjoint graph. So the y-axis is 50 hours skipped to 250 hours. So if you can imagine the graph is actually very skewed. When I made the graph, GPT-5.6 was like a very big outlier. So I had to compress the graph. But this only works if you consider that GPT-5.6 cheated on some of the tasks. And so we'll be talking about why AI models cheat and how do we solve these issues. But yeah this plot is very useful to showcase the capabilities of these models.

Daniel: So previously this is 50%. If a model can complete the task with 50% of the time to 50% accuracy if you want to actually oneshot the model, so you just ask the model implement X or implement Y, and you want the model to do very well, then you want to look at the 80% success rate. If you look at the 80% success rate it kind of drops quite a lot. So you can see that previously Mythos is around 16 17 hours, now it only can do three hours. So if you prompt a model and you want to have like a oneshot example, you just trust the model by asking it implement, I don't know, page rank or something, implement some sort of rag system, fine-tune a model or something like that. It can only do a task that will take a human three hours to do. And so that is a problem with AI models. Generally speaking, if you want to use AI models very well, you need to prompt it at least like five times or something. And each of those times assuming they're independent the success rate is much higher if you're prompted many many times. Right, you can't just call the model once and expect it to do work to do well, you need to call it multiple times. And you can also work out the probability of it succeeding. You know if the model is 50% accurate then it will be 50% failure then it's 1 minus 0.5 to the power of five or something like that. If you do five turns and then your success rate jumps to like 97% or something. So you need call the model at least five times for it to be very effective.

Daniel: So previously these are linear, this is a linear trend on the y-axis. It's not just linear. If we log the y-axis you can see that it's more exponential progress. So it's actually a straight line fit to the entire progress of AI models on the meter time horizon. Benchmark you can see that it's very clear that AI models are getting better and better over time. We also added GPT-5.6 with the cheating and no cheating and also claude mythos are accentuated that. And you can see I you don't need now you don't need to fake the y-axis, you don't need to do like a disjoint y-axis. If you do that you can see that models are getting better over time. And supposedly if this trend continues these models will get better and better and much better. Yeah, so the question is if the trend continues, that's the fundamental question. And it's not just one specific task for this benchmark that you can see that models are getting better over time, across all benchmarks models are getting better over time right. So like GPQA diamond it's kind of plateaued, it's kind of already saturated as a benchmark but over time it does very well. Every single benchmark you see models are getting better. Live code bench, math tests, even Tesla's self-driving I guess is also has like a doubling time of 17 months. So every single 17 months the models will get better and better. Double their capabilities. So over time all these models in every single subject every single area it will get better. Um so I guess the main question is if we assume every single subject every single area the models get 100% like approaching 100% accuracy, is this AGI? Um so that is one of the fundamental

Speaker A: questions that people ask you know if we just get better on benchmarks um is this AGI um what happens if we get better on all benchmarks you know every single benchmark that human humanity has created it just gets better on all of them. Um yeah but so this is a you know very good plot show well I guess chart showing all of the different types of benchmarks and they all get better over time. everyone's favorite I guess artificial intell uh you know artificial analysis benchmark showing you know artificial intelligence getting much much better over time as well you know fable I guess is I guess the best for now um although not everyone can access it currently but anyways it's for now it's the best um and you can see over time that you know these models are getting better over time as well um and you know like this plot showcases um a very useful indication you know like how do we like you know benchmark you know is this benchmark actually good um in terms of like you know showcasing the capabilities of models as well. Um and we'll be also discussing about that as well. Um on the other hand yes models are getting better over time. Um but there are some things which models are not very good at still for example long context is not doing very well.

Speaker A: Um so you know most models you might say okay Gemini has 1 million context length. You know GBD has 1 million context length. Claude has 1 million context length. But should you actually use all of the 1 million context length? Um so there are actually benchmarks to showcase that if you use for example GBD 5.5 um you know if you use 512 context your accuracy reduces to 50%. Um so if you use you know 512 context you will only remember 50% of the facts that you wrote in the previous context. Um so maybe that's not a good idea to use the full context. Um you can see opus 4.7 um 4.6 4.7 is the very last orange line. Um so at the context length of 256K it goes to 0%. Um so this might be a benchmark flaw. Um so maybe don't trust the benchmark too much. Um but it's good to look at the benchmark overall. You know where is the model's capabilities for long context. Um the blue lines I highlighted are open source models. You know deepseek gl 5.1 other models. Green is Google's models. Um but you can see in general you know models are models definitely do degrade over long context. Um so if you you know for example if you set like a you know automatic compaction area I would not suggest you to use all 1 million context maybe maximum 600k or something um and then compact it and then continue your you know coding session um but I would yeah but in general you know this plot shows that long context still has a very long way to go um and if we want to have long context you know capabilities um labs I guess will have a lot of time to fix this problem.

Speaker A: Yeah. So another plot is you know just showing open source versus closed source. So open source still has some way to go for this you know long context. Um so open source is blue line and the black lines are like you know closed source models. Um and you can see in general open source does okay but there's definitely much more room for improvement. Um I guess compared to Opus 4.7 it's better. Um but you know maybe this benchmark does need maybe there are some flaws in the benchmark as well. Um yeah, but overall you know this plot shows that long context definitely still has more room for improvement.

Speaker A: And also you know like if you looked at the plot previously you know this meter plot um I'm not sure if you can see that before 01 preview there is actually a plateau of performance. Um and so if you can see you know GBD4 to GBD40 there's not that much performance improvement. Um and so this time frame around one year um was when you know the labs were confused on what is next um you know before 01 preview which showed that reasoning was very important they didn't actually know what to pursue next um and so for one year the models kind of like plateaued um and so I call this the intelligence plateau the hypothesis that you know you know assume that we never have discovered reasoning then maybe air models would have like plateaued um but because we have discovered reasoning you know we have shown that models can do reasoning capabilities we have continued the trend continuously um and so normally I don't know if this is like luck um or if this is a self fulfilling prophecy um so I don't know if you guys you know the moor law um you know mos law has continued um not because of the law but because people know that it must continue and so people invest money into the resources to make the law continue um and so this kind of like shows that you know we might have been in of the world where models have stopped improving.

Speaker A: Um but you know with the launch of 01 preview you know I guess models have went back to trend. In fact I made a plot showcasing you know assuming we did not discover reasoning or 01 preview. Um then the black line was the supposed you know capabilities of the models. You can see I made it into a S shape um like a you know a sigmoid type shape. Um and if you know if we didn't discover reasoning then models definitely will taper off in terms of capabilities right we'll only have a model that's as capable as claw 3.7 sonnet I guess or 01 or something like that um but you know luckily because of reasoning and this new paradigm of scaling you know the green line is the new scaling law um and you can see previously the black line the doubling time was actually around seven months so every single seven months the capabilities of the models double um but now it has shrunk to 3.5 months. So every single 3.5 months you just need to wait 3.5 months and the models will get double better, right? Better by two times. Um and that's quite striking I guess.

Speaker A: Um so the main question though is will the green line continue as a straight line? Um that is a fundamental question that labs are still struggling on. you know what happens if the green line again you know the green line again goes as a S shape you know that's possible um but you know we don't actually know if this will happen you know if the green line will continue scaling you know going all the way up to infinity I guess or would it be like an S shape um and this is you know many researchers are you know I guess have sleepless nights you know what is the next you know what is the next thing afterwards after reasoning after 01 you know what is the next thing afterwards um and you know Many researchers will need to like you know I guess think about this. Um yeah but you know this plot is very you know this is one of my favorite plots because it shows that you know AI progress can continue over time with new ideas and innovation. Oh yes. So does anyone have any questions for the first section? Um yes.

Audience: >> So we came all the way to one trillion right? Do you think the next jump if we need do we need like 10 trillion parameters when we'll see the jump or hardware will be the limitation that

Speaker A: >> yes that's a great question. So the question was you know models we're currently at one trillion parameters do we need to go to 10 trillion parameters or more for models to be even more capable? Um so the scaling laws does say that you know if you multiply the parameters and the data size um generally speaking this number if you increase the number you will get the models become more capable. So yes you can increase the parameters by 10 times and in general your performance will increase. Um however the view is there is going to be diminishing returns. Um I feel like you know it's not just the model size times the data set size. It's actually a ratio um some sort of like power law when you multiply them. So you actually get diminishing returns over time. So yes, you're right. If you want to have actually I'm not sure the exact law, but if you want to have double capabilities, you do need to 10 times the parameters. Um and then if you want another double, you have to 10 times it again. So it's 1 to 10 to 100 trillion parameters. um if you want maybe that's not a good way to scale. Um maybe instead you know instead of making a 100 trillion parameters

Speaker A: ... some sort of new algorithm or new architecture could solve that problem. Um but you're right like if you're a lab you want to do something easy and so the easiest path is to just make a 10 trillion parameters. Um but I would say like you know maybe a new algorithm will be better. Um yeah any other questions? Yes.

Speaker B: >> So you do think that we are approaching the limitation of next token prediction.

Speaker A: >> That is a good question. I would say that for next token prediction it's very powerful because you can essentially the human language is extremely powerful and it doesn't have to be human language. It can be you know maths coding you can just predict the next word and in order to predict the next word or token you need to know everything about that token or that word right so like I think IA was talking about like you know Ilia Satska he was saying like you know you need to have you need to make a weld model in the model in order to like predict the next word so I still think next word prediction still has a lot of way to go for example if you see this plot you know if we didn't have reasoning I guess okay maybe it would have plateaued But because we have discovered this new methodology you know reasoning and trying to like scale even more on next word you know next word prediction we have you know went back to trend um I feel like so the main question is if we don't have next word prediction what is next um that is the fundamental question most I mean I'm not sure like you know I'm not certain what's what's the next thing I feel like next word prediction is just extremely powerful because it's very easy to formulate and you can just like you know you can have like you know because attention is very powerful as well. You can have, you know, this special cause of attention mechanism and it's very efficient to train. So, I'm not sure I think the main question is I'm not sure what's next. Um, I guess researchers will like, you know, they're trying to scratch their heads, you know, what is next afterwards? Um, yeah. I I Yeah. Yes.

Speaker B: >> Just a follow up on it. Do you feel like we are in the same era like how we attention came out?

Speaker A: >> Right. So, attention like we don't know what's next. Yes, that's a fair followup. So, um, you were mentioning how it's kind of like LSTMs or the old AI world. We don't know what's next afterwards. Um, that's a fair point. I feel like so like, you know, previously this example, right? So, after GBD4, it was just pre-training, some, you know, supervised fine tuning, some ROF, you know, some RL um, and they waited one year until 01 preview. So in this one year of fog you know the fog of war we don't know what what was next and so researchers you know were scrambling you know do we do the reasoning process do we make pre-training better do we make the model bigger and bigger and bigger you know they tried all these experiments um and reasoning was the one that won I guess um but I think like I think the main question is is the green trend going to continue at the current time it looks like it's continuing once we see models starting to taper out in intelligence, you know, in capabilities, then we'll go back to the, you know, olden days of like, you know, this one year waiting period. But I think for now, these models seem very powerful. Um, yeah. So, like I'm not sure if this will, I mean, if you look, okay, if you squint at the plot, I guess maybe we're tapering out. Maybe um let's not consider the GBD 5.6 cheating example, right? Let's remove that from the plot. Um, but you can see the GBD 5.6 Mythos, you know, 4.6. They're kind of all I guess they're kind of tapering. Um so maybe as a I mean I don't know if we someone wants to bet on this but you know maybe models have tapered out but we're not sure. So we shall wait a few more months and see. So let's wait 3.5 months. If we wait 3.5 months and see the models do not improve then we have tapered out. Um but remember we only need to wait 3.5 months. Um so then this law will fail. In fact, if you wait seven months, if you wait seven months, so double the time and models have, you know, just assume you know that dotted line that if if the models just follow the dotted line, okay, then we have tape it out. And I would agree that, you know, we'll have to design something new in, you know, make some new invention or something like that. Um, but for now, you know, for now looks like it's doing fine. Um, yeah.

Speaker A: Okay, next section. Um, so every single section we can have questions, so you can ask as many questions as you like. Um the next section we're going to talk about is open versus closed models. Um so artificial analysis has this very cool plot showcasing the performance of open source. So open source is the blue line. Um so open source is the blue line and closed source models is the black line. Um and you can see that open source does lag. You know open source definitely lags over time.

Speaker A: Um another very good benchmark is called the weird ML benchmark. Um this also shows that open source models lag closed source models right the blue line is open source models the green line is closed source models um and you can see over time you know the x-axis is release date of the model and the y-axis is performance and you can see that open source models kind of lag close source models and why the weird ML benchmark I'm not sure if you folks actually know about this why the weird ML benchmark um it seems like the weird ML benchmark is a very good indicator better than other benchmarks and the reason the reason why is you know previously I mentioned you know previously this graph right reasoning the reasoning models are the green line and in the black models are the non-reasoning models and you can see that reasoning models double you know reduce the time of doubling time to 3.5 months previously it was 7 months um interestingly on the weird ML benchmark these reasoning models didn't actually do better it didn't actually change the trend um all it did was make slightly better. Um and so this weird ML benchmark seems to be more robust. Um and that is why you know this benchmark is very useful.

Speaker A: Um in fact if you go on the Twitter bus um before GLM 5.2 got released um most you know most of the Twitter people said oh you know deepseek you know deepse if you see very if you squint okay I think I have a plot. Oh yes if you squint deepseek and Kimmy are in that little corner over there. um you know deepseek those three models the three whales are deepseek you know flash deepseek pro I think one of them's max mode or something like that um and also Kim's over there as well so before GLM 5.2 two got released, you know, on the Twitter verse, everyone kept saying that open source models are much worse than closed source models, right? They're not lagging, you know, they're not just lagging, they're much worse because of this benchmark.

Speaker A: Um, in fact, if you look very closely of the weird ML benchmark, all of the top models are closed source labs, you know, like Fable, you know, GPD 5.5, whatever, you know, all of these are just very, you know, it shows very clear that open source models are not doing very well in terms of this benchmark. um until GPD 5.2 came along um you know number 15 is GPD 5.2 and it shows that actually open source has came back um and GPD 5.2 too kind of shocked the world. Um that you know I guess open source has not died. Um and you know deep yeah so in general this worked very well you know deepse you know GLF2 showed that you know open source does very well still.

Speaker A: You can also filter out by country. So by country you can see that the black line is United States you know the US models. Um the dark red line is the Chinese labs. Um and you know there's other labs as well. um you know French, South Korean labs and stuff like that. Um but you know over time it shows that these models um you know the US labs seem to do very well over time. You know they they're always at the frontier and then the Chinese labs like to catch up over time. Previously you know I mentioned you know the um you know the plateau before you know before 01 preview got released. If you actually look at this

Speaker: plot um there is something called the open source draft. Um so after 01 preview got released open source labs did not know how to replicate 01 preview. They have never you know they don't know what is reasoning. So I'm not sure if you okay this is a few years back um but on Twitter you know open kept talking about oh you know 01 preview was extremely powerful um you know every single tweet you see every single day you know they show that 01 preview was very powerful. Um and so for one I think it was six months to eight months um open source models open source labs they got confused on what to do next. Um but then as everyone knows deepseek R1 came along um and they showed that even for open source models you can train these models to do reasoning gpo um reinforcement learning and it does very very well.

Speaker: In fact, if you take this plot, you know, the the black line minus the blue line, if you just minus it, you get this plot. Um, and you can see this is how many months behind open source is. Um, and you know, over time, um, you can see like, you know, after 01 preview got released, um, you know, it kind of skyrocketed. Um, you know, the open source models were very, very lagging in terms of, you know, behind closed source models. Um and so like when Deepseek R1 got released then the open source labs knew okay we can also do uh 01 type reasoning. Um and that is why recently you know the the time between closed source labs and open source labs have started decreasing again. Um yeah so this is slightly outdated. This is like May. Um so I think now it's actually four months with the release of GLM 5.2. It's around four months now. Um so open source labs lag behind closed source labs by around four months.

Speaker: There was actually a very nice plot you know doing some sort of regression. So some sort of like trend extrapolation. Um according to this plot um if you extrapolate the trend by December this year open source models will 100% catch up to closed source models by this year December. Um but you know who knows I guess maybe maybe open source maybe we can have an open source model as powerful as the best closed source model by December um you know if this trend continues um so I guess the question is will the trend continue um it's always about will the trend continue

Speaker: um and you know may most of you maybe may know that you know open source some of the open source improvements in technology you know improvements in capabilities are via distillation you know so some of the open source labs what they like to do is they like to call the models you know core the frontier models like opus or GPD and then use the traces to train your model um so this is a common methodology that labs like to do um I wouldn't say this is a bad method um but it is a method that you know some closed source labs like to look down upon you know they like to stop you know their view is you know we should not allow these open source labs to like do this training um and you know get away for free I guess in terms of training cost.

Speaker: Um but you don't actually have to do this approach. Um so most labs when you do distillation there are two different types of approaches. Um the first approach is you need to have the logits. You need to actually have access to the full logs. Um and unfortunately most labs do not actually have that right. So like labs will not give you the full logs. Um instead you only get the reasoning traces that are summarized um and the final output. Um, and so these, you know, these open source labs, they're not just, you know, they're not just training on the, you know, Opus output, right? That's just, that's silly. What they do is they use GRPO or reinforcement learning to recreate the traces. Um, and so because you you have the final output, which is the answer. All you need to do is use GPU and RL to create the reasoning trace automatically. Um, and so that's kind of how they train these models. Um, and so you don't actually need to like access the logits or the weights of the model. um that's not necessary.

Speaker: Um yeah, and you know, one of the most important factors of you know, these large models is, you know, as models get bigger and bigger and bigger, you can't run them on your local device anymore. Um it's extremely complicated to run. Um and so we do something called dynamic quantization where essentially you take a model, you quantize them down to one bit. Um but the trick is you don't quantize every single layer to one bit. you quantize some important layers to 16 bit or 8 bit or something like that. Um and so if you quantize the whole model down to one bit you will get 0% accuracy right 0%. Um but the trick is if you do dynamic quantization so if you look on the you know this is a three-bit Deepseek model um a three-bit one you get 75.6% 6% accuracy, a three-bit one. In fact, if you do dynamic one bit, um you get 57% accuracy. Um so we show that you know if you do something called dynamic quantization where you quantize the model down smartly, you can recover accuracy. Um and this methodology will become even more important when models get larger and larger and larger and larger. if you plot the paro you know efficiency um there if you don't do dynamic if you do you know some other dynamic quantization methods it does okay um but we showed that if you smartly choose the layers it does even better

Speaker: um I'm not sure if you folks have followed but GLM 5.2 we also released dynamic quantizations for that we showed that GLM 5.2 2 can quantize very well. So if you look I think this is oh this is an animation. Oh it works. Um but yes you can show the animation you you can see the animation a one bit GLM 5.2 model and this is one bit um and the one bit model is literally 86% smaller. Um so it's 86% smaller than the full 1.5 terabytes. Um and it still managed to do very well on one of the prompts. Um so it shows that the models are not dumb. Right? If you make the model 86% smaller, it does not get 86% dumber. Um, it only gets 14% less dumb. Um, and so it shows that, you know, if you do special tricks to compress the model, the model still works very well.

Speaker: Um, and we also compared to Opus, you know, we compared to Opus 4.8, we compared to GBD 5.5. And also, you have to notice that for G 5.2, I use high reasoning mode. You know, for Opus, it's extra high. And for you know GPD 5.5 is also extra high. Um and so like you know there are different reasoning modes as well which we can also um see. Um and all of these are oneshot um so we do not like prompt the model like you know 50 times or something. Um this is just one shot directly. Okay so the next I guess the open source versus close source section is done. I guess any other questions? Yes.

Speaker: Um so the question was which parts of the model do we quantize to lower bits versus higher precision. Um so in general um we did actually a lot of research on this. So if you look at the quen the quen 3.5 architecture there are some layers which is the linear attention layers. Um the linear attention layers should never be quantized. If you quantize the linear attention layers down you will definitely suffer in long context. Um so in general the linear attention layers need to be left in 8 bit or 16 bit. Um that's for example um another like if you look at the model layers um some layers can be quantized down heavily to one bit. Um and the reason why is because these layers are kind of like filler layers. Um and so they don't actually do anything. Um and in order to check whether a layer does something or not, you do need some sort of collaboration data set. So you need you need to have some sort of like representative data and pass it into the model um and you can get you can get the um outputs after each layer and then you can see okay does this model at this specific layer you know does it change that much um and if it doesn't change that much okay maybe just quantize a layer to one bed um but if it does change dramatically then you need to be careful um you you cannot quantize that down to like one bed or whatever um so there are actually many we actually publish a lot of like blog research on

Speaker A: Um we show I think there was we also show for example you cannot quantize the vision layers down. If you quantize the vision layers down you will make the model really bad. Um if you give it a you know if you give it a picture of a train it will say it looks like a beach for example. Um and so it's you should never quantize the vision layers, the audio layers. Um and only the language the language model layers you can like quantize. Um but there are many tricks in order to do that. Um yeah

Speaker B: correct. So the question was if you do distillation um you you might have done worse on other topics um but you know only if you for example if you just do coding it will just do good encoding and then the rest gets very dumb. Um so that's a fair point. Um so I think that the main trick is you will need to do many many examples. You will call the model like you know 10 million times. Um and so like the trick is once you call the middle model 10 million times with high diversity of questions in general um by using the pre-training argument um the model will do well on other tasks. Um so the reason why pre-training does very well um is because it has learned so many tasks that it can interpolate the missing holes. Um for example, if you just train if you just pre-train a model with just maths questions um assume you do only maths. Okay, maybe it's not going to do very well, right? And it's not going to do very well on every other task. But the trick of pre-training is it does maths, coding, law, you know, every single imag, you know, every single topic you can imagine. And the trick is because it has so much knowledge, it feels the holes of the things that it doesn't know. Um, and so for distillation, you also need to do the same approach. You need to sample, you need to sample well. Um so for example instead of doing 10 trillion tokens sample you know like 1% um and then call the model. Um yeah so that's kind of how the labs are doing that.

Speaker B: Um that is a very good question. So instead of doing one big quantization can you instead prune the model like you know delete some layers entirely. Um so in general from our research pruning does work. There is a very big problem though. You need to retrain the model. you need to continuously train a model after pruning because you have deleted an entire layer. Um and so if you delete an entire layer, you will need to do like you know qat or further fine-tuning to push the other to push the other weights to have more knowledge. So that is the only problem where if you delete layers um if you don't delete layers when you do you know dynamic dynamic quantization it's called post training quantization. So PTQ you do not need to do any training at all. if you do you know quantization um but if you do prove the layers you do need to train um so that is one of the problems um yeah

Speaker B: yes that's a great question so the question was you know because open source labs you know they use closed source models the gap will never actually go to zero um and so I partially agree and so the main argument was labs open source labs the easiest way is to do distillation however you know if you for example if you were an open source app you will only use that approach to firstly enter the market but as longterm you know as long-term safety as a long-term safety net you will not do this approach um instead as a you know instead you will do you know for example generate the answer get the question for example you know you will get data from a call or scale whatever you know have some sort of like large data labeling army or something I don't know um and so like in general because currently some of the labs so they don't just do distillation right so they're not just going to call the model 10 trillion times you know and just do distillation. They also augment the training data with their own approach. So I will be talking about the GLM approach maybe like later um but they did invent some new approaches to do very good reinforcement learning and GRPO um and because GRPO and reinforcement learning um you know is open source these labs just use these methodologies to make the models better. So you don't so distillation is only one part of the training system. Um and it's not I would say that assume distillation disappeared. Okay, maybe open source labs maybe increase you know it's not four four months maybe eight months um but but that's fine because you know we always have some sort of innovative and new approach you know deepseek might invent something new um and so like you know GLM ki all of them Google you know even the American open source lab they'll have some new innovation um and so like I think like yes if you stop distillation it will increase you know the you know four months to eight months but I still think that is fine Um it's just a delay you know and then the delay will go back to like four months. Um yeah good question.

Speaker B: So the question is if dynamic quantization is always better why do people not always do dynamic quantization? Um so it depends on the definition of dynamic quantization. So for every single lab they will have different approaches to dynamic quantization. In fact, I'm actually going to talk about that. Um, I was going to talk about that in the benchmaxing and accuracy minimizing session. So, I'll be talking about that. Um, so I will your question will be answered later. Um, yes. Okay. One more question. Yes. Yes.

Speaker B: So, the question was for consumer grade GPUs, you know, what are the open source models in terms of like, you know, the parameter size capabilities and stuff like that. Um, so for the open source community, you know, the most popular models are probably Quen 3.6 6 35 billion um 27 billion GMA you know Gemma's 26 billion um GLM 4.7 flash the smallest type models um and I feel like these small models are actually very powerful um so okay I don't have wait I don't think so I have a plot um but essentially these small models the biggest problem oh actually I'm going to talk about this as well the biggest problem of these small models are they fail very bad at tool calling because they have tool calling issues um they loop continuously um and the biggest problem is because they're small and that is why they have these problems um but we can counteract this um and so one of the things I'm going to talk about later is the model becomes not important anymore it's the harness or the tool that is actually the most important thing um how do you actually call the model um that actually affects the most accuracy of the model um so not actually the model itself um but I'll be talking about that as well um yeah okay I will continue on. Um, there were always questions after each section. Um, uh, yes.

Speaker B: Oh, yes. The next section, the fun section, throughput maxing. Oh, actually, I think I did. It's supposed to be 2x. I don't know. Whatever. Throughput maxing and and accuracy minimizing. I thought it was like accuracy mining, but there's no such thing. So, it's called accuracy minimizing for now. Um, yes. So, this part actually I really like. Okay. I'm not sure if you guys can see it's a bit oh whatever. Um this shows the parade efficiency of cost of the cost of the model. So cost is um cost is the x-axis. Um and the y-axis is the arena score. So this is like you know Ella Marina's arena score. Um and this part I really like. So I don't really you know maybe you see like arena scores you know Ella Marina scores between each model. I don't really like that. It's not it's not very easy to see. Instead the better approach is to plot every single model on two axes cost versus accuracy. Um and you can see Fable does very well right so Fable does very very well on that plot. Um but you can see there is a paro trend you know like Gemini 3.1 preview is over here you know Opus 4.6 is over there as well. There are some other models as well when Fable got released. Okay. Well, now it's banned, but anyways, when Fable was released, when you know when people tried it, they noticed that it's not that much better in terms of actual capabilities. Um, you can see, you can see, but however, people really liked the front-end design. You know, they said

Speaker A: if you called Fable, it was very, very good for UI UX front end. Um and in fact if you look at the LM Mariners chart you can see it it was a very big shift in terms of front-end design. Um GLM 52 is also there if you can see you know it was part of the par paro trend. Um but in general for these large models they seem to have they're not going to be do they're not going to be doing that much better on general tasks. Um however for UI and designing Fable seems to have done very very well. Um, and so you should use Fable for your designing. You you should use Fable for designing, for UI, for UX, whatever, HTML, JavaScript, but you should probably not use Fable for the rest of the tasks because it is very expensive. Um, so you know, use some other models instead. Um, and you know, however, yes, okay, you know, some other models, you know, like, okay, this, you know, this shows that Fable does very well on UI and UX.

Speaker A: Um but how about over time um you know how what do you know anthropic their view is we need to maximize throughput right maximize throughput but also maximize accuracy um you know they want to like you know serve more people um but sometimes it doesn't actually work um sometimes they actually reduce accuracy um and so you can see there is a I don't know if you folks know margin labs um they have this very cool they do they do su bench they benchmark codecs they benchmark codecs and clawed code with the models. Um, and this accuracy over time for these models. Um, and the dotted lines are the release of the new models. Um, so there's actually another um, there was actually a dip in Wait, can you is there Oh, okay. The mouse is there. Um, I I think it was over here. Um, I think it was over here that feeble got released. Um, so there was actually another dotted line. Um, there was actually very interesting trends you can see. The first one is um every single time there is a new model release this this you know daily tracker seems to decrease in accuracy. Um and so if you want to predict when a model gets released from anthropic you can use this as an indicator um of when the model gets released. it worked very very well. Right? So like essentially if you were over here the dipped in accuracy over a very long period of time was because fable got released. Um and over here I think that's opus 4.8 I think. Um I think yeah I think that's opus 4.8. This is opus 4. Uh 7 and so on. That's 4.6 I think. I whatever um I don't remember exactly but um but you can also see that there is ginormous dips of accuracy. Um, and it's not just like one day or two days, it's for a very long period of time. This is also Codex. Um, so they also do codeex benchmarks. Um, and you can also see that over time. I don't know if you can squint, but you can see that actually Codeex has been getting worse if you plot the trend, right? If you can I don't know if you can squint, but if you draw a line, it seems to be getting worse. Um, so I'm assuming OpenAI is investigating this as well. Um, okay.

Speaker B: >> So this is different model. This is codeex.

Speaker C: >> So this is using 5.5.

Speaker D: >> This is using

model.

Speaker A: >> Correct. It's the same. So what this benchmark does is you randomly sample 50bench questions. Sweet bench is very large. So you just sample 50 of them and then you call the model to answer it. Um and then you record accuracy. Um and so obviously you know every single day there's like you know daily variations. Oh, it's not it's not that useful because you're only calling 50 questions. Um, so the trick is to look at the trend. Um, and the trend uh h maybe open should investigate this. Um, and you can see the trend for you know anthropic is also not very good. Um, in general oh so sorry this is not the same model. Um, these models change my bad. Um, so it's the same harness but the model changes. Um, so this dotted line is GBD 5.5. Um, so everything over here is GBD 5.5. Everything over here is GBD 5.4. Um I think this is 5.3. Um and so on. Um but it seems like the model's getting worse. So I don't know. This is probably just on this benchmark, right? On the Sweet Bench Pro benchmark, it's getting worse. Um but you know, I wouldn't really trust these benchmarks. The best way is to look at the degradation. You know, the sudden drops. You know, for example, Codex dramatically dropped over here. I don't know why. Um and you know clawed you know clawed code was very bad for a few weeks over here or over here right. Okay. Yes.

Speaker A: >> Yes there is a confidence interval. I did not plot it but this is 50 tasks. So every single day they call a 50 tasks randomly. So they will sample 50 tasks. Um and so you you should not look at this daily. This is daily. So every single day is 50 questions. Another 50 questions. another 50 questions and so on. Instead, you should do like a rolling average, you know, some sort of rolling, you know, 7-day average. Um, that's a better number. Yeah,

Speaker B: >> really. I can see it from here. It's like decreasing.

Speaker A: >> It's it's

if you look at the if you do the seven moving average, I I'll probably get the pot later. It actually is decreasing. You can see it um if you can see I don't know if you look at the top peaks of the you look at the top peaks and the peaks are decreasing.

Speaker B: >> Okay, how about the bottom peaks?

Speaker A: >> Okay, I agree there is random noise. So the trick is you need to the moving average and if you look at the moving average you can actually see it's decreasing. I I'll probably I'll get the plot later. Um you can you can search it. It's so go to Margin Labs, search in Margin Labs codeex claw code benchmarks and they do show weekly the weekly trend but I'm just saying this is not this is not to say that the model is getting worse. This is just to show that accuracy that you know the sudden dips the accuracy of these models can decrease. Um and the question is why you know for example why did claude code over a few weeks why did the performance decrease like why that's the fundamental questions. So that is one theory. A theory is they might have accident you know that before the model release they are doing testing and so they might have like you know act you know some of the some of the queries they route to opus 4.8 eight

or fable or whatever. And the problem is they did not. So the main question is if you do route to another model, why did the accuracy decrease? It should actually get better. And so one of the theories is theory one, they forgot to edit the system prompt. And so the system prompt for Fable was different, but then they used the wrong system prompt for, you know, for Opus 4.8, and that is why the accuracy decreased. Um and then after the model got released the accuracy went back up because they used the correct system prompt. That is one theory.

Speaker A: Um the other theory is the other theory is okay we're actually going to talk about this is it's actually they're doing tricks. You know they did quantization but they didn't do dynamic quantization. They did some dumb quantization. Um you know they some GPUs are broken for example. You know they use the wrong GPUs. Some of them have like you know bit flips or something. I don't know. um they have like a new data center and then that data center just by chance has lower accuracy. Um in fact there is actually okay I'm going to talk about this actually. Um yeah but there are many many theories like you know possibilities why this could reduce an accuracy. Um actually I I think it's the next plot. Yes the next plot. Um oh well the next slides. Um so actually when was this? I don't remember. Um it was a few months ago. Someone from AMD actually made an issue on chord code you know during this dip. I think it was during the before um a very large dips in accuracy and they actually asked Claude, you know, they asked the Claude team, why is there a noticeable dip in accuracy? You know, why why is that? And Claude actually wrote a in April 23, they actually provided details on why they had reduced in accuracy, right? So they did a postmortem on what happened with Claude. Um and the reason why is because the thinking trace got deleted after the second you know when you when you ask

Speaker A: The second time, the thinking trace got deleted and it had a bad system prompt. They found out that that was why the accuracy got degraded. Somehow in Claude Code, the second time you ask a question, the previous thinking trace got erased. I don't even know how they did not find this, but oh wow, according to them, Claude now has this internal benchmark, so they will use more internal investigations to test that next time if there's a new model, this won't happen ever again. These things do happen over time. For this specific example with Claude Code, the harness itself was the problem, not the actual model, right. The harness, the thinking trace got deleted, and they had a not very good system prompt. And that is why the accuracy actually degraded.

Speaker A: So we found one answer why these models got worse. They also released in September 2025, right in September 2025 they showed that it was actually due to a hardware problem. So in their compiler they used TPUs. Anthropic likes to use TPUs and GPUs. They showed that the same software stack for GPUs and TPUs actually produced different results. And so for the TPUs it actually was different sampling. And for the GPUs it was a different sampling mechanism. And so that is actually why they had decrease in accuracy during September sometime. Because they actually had different hardware. And so you need to, like, once you have different hardware accuracy also changes.

Speaker A: So I think the main point is the harness, the implementation, the tool is now the most important. It's not the model, right, the model is useless. Most models you know, if you look at open source versus closed source, models are generally the same. The difference is how Claude Code is made, you know how Codex is made and used. And so that is actually the most important factor. It's not the model anymore. And so like you know, as we have seen, if they accidentally botched the harness, you will get reduced accuracy. And so definitely for large labs, I'm sure they know these problems and they're working on it. But I feel like these are still very hard to fix.

Speaker A: Hopefully I answered some of people's questions on the harness, you know, the accuracy. So there's actually reasons why accuracy got degraded, but you know it's not just closed-source labs; across open-source model providers the accuracy changes. So if you look at this plot, this is from OpenRouter, this is DeepSeek v4 Pro. Most inference providers, what they want to do is they want to serve you the highest throughput, right, with the cheapest price. They want to give you, you know, 60 tokens, 120 tokens, 1,000 tokens per second, right? They want to give you the fastest. But did people actually bother to check accuracy? So that is the fundamental question. You might be getting 10,000 tokens per second and there is no model. So the main question is you need to be careful of what you use from these inference providers. And so for DeepSeek v4 you know there are two benchmarks which OpenRouter ran. I think it's sorted on Tau-bench, and the green one is GPQA. And you can see that in general some of the inference providers are not doing very well. So before you use an open source model, please check the accuracy.

Speaker A: And also one of the biggest problems of this is every single time, you know for example with Claude Code and Codex, you can benchmark accuracy over time. And the good thing about closed source labs is they control the supply chain. The biggest problem of open source is there are so many suppliers and providers of these models that sometimes what happens is people get turned off and they get very annoyed that the open source models do not work very well. So everyone in the ecosystem keeps saying that closed source labs do much better than open source, but it's not because of the model, it's because of the inference provider. The inference provider is to blame that they are causing the downfall of open source because they're giving a bad name for open source. So I would check whatever favorite inference provider you have. This benchmark was run I think yesterday by OpenRouter, so this is daily data by OpenRouter.

Speaker A: So whatever favorite inference provider you have, please tell them not to, you know, reduce accuracy that much. This is GLM 5.2. So GLM 5.2 as well shows different accuracies. You can see the plot on the right shows most inference providers are throughput maxing, but they are accuracy minimizing, that's where the phrase comes from. So they do not care about—in fact, look, the highest accuracy is 76.4% and the lowest is 62.4%. So there is a 10% gap between the highest accuracy and the lowest accuracy. And so as a call out to inference providers, you know, please increase accuracy before trying to make things faster. You do not want a model to be very dumb and it's like 10,000 tokens per second. We can make it 1 million tokens per second and there is no model—just call a human or make a fake or something. So the main point is we need inference providers to do good in terms of accuracy, otherwise this will make open source have a very bad look. Oh okay, that's the end of the second section. I guess that was a bit of a rant. Any other questions for this? Yes.

Speaker B: For a new organization that wants to use like the open source model, do you suggest using an inference service provider, or do you suggest downloading from Hugging Face and then using like model or some kind server to implement yourself? Like what do you suggest if any new organization comes and asks you like how do you use open source model?

Speaker A: That's a great question. So when an open source model gets released, you know, how should you use it in terms of accuracy, throughput, or whatever? So in general, open source has come a long way. So for example, we did report bugs in Gemma 1, Gemma 2, Llama, Mistral, you know, OpenGPTs—every single one of those models had bugs. And so the good thing is, we will help the labs before they release a model to fix some of the issues. So every single model you now have has some of our fixes. So that's a good thing. But in general, if you have an open source model, I would use Llama CPP for example. I think Llama CPP and Llama server is probably the most bug-free system. So I would suggest yes, you should download from Hugging Face. Use Llama server, use Llama CLI, you can use LM Studio, whatever is your favorite tool. But you should, yes, you should download from Hugging Face. In terms of like, if you're a large enterprise, generally speaking, what they like to do is they like to wait one week. So most enterprises, they'll wait one week for all the problems to be fixed. And then they will use the model. But in my view, that is not a good approach. I would say if everyone waits one week, then like how do we fix the bugs? Because only at scale, then we can see the bugs. And so like in general, we need everyone to start trying these models earlier, and not like wait one week, wait one month, you know.

Speaker A: don't do the waiting approach. Um but I would say like in general the enterprises what they like to do is just wait one week. Um yeah that's like common practice. Um, yes.

Speaker B: >> So, okay, the question was why would the model performance degrade before a model release? Um, these are just hypothetical question hypothetical theories. So, every single model has a different system prompt. So, opus 4.8 8 Opus 4.8 system prompt is very short. Um but Opus 4.7 system prompter was extremely long. Um so the theory was this is just a theory that anthropic via claude code accidentally routed some of the models to Opus 4.8 right they use opus 4.8 as testing right they need to test opus 4.8 But they used Opus 4.7 system prompt. So they used the wrong system prompt and that is why accuracy degraded. That's one theory. Um, another theory is actually I think that's the actually I thought about it. That's probably the only theory I had. I'm like thinking hm is there another theory? Um,

Speaker A: >> I guess the harness itself like you know sometimes the harness itself the harness was was designed for Opus 4.7. Um and during when they were going to release 4.8, they need to collaborate the harness, right? They need to change the harness um for 4 4.8 to make it work. But the problem is you're not allowed to publish it, right? You're not allowed to publish it and give it to people because otherwise people will like, you know, go into Twitter on LinkedIn, you know, everywhere. Oh, I can see 4.8 is going to be released. You know, everyone's going to be screaming, you know, 4.8's coming. 4.8's, eights, you know, were getting released and so maybe that's why accuracy decreased. It's they update they did not update the harness. Um or the other option is they up they already up they silently they silently updated the harness before the new model got released and it regressed you know it reduced accuracy. Um I don't know like to be honest I you should probably ask anthropic that question. Um or but I think in general in general the dips the dips don't always correspond to like new model releases. Some of the dips are actual issues like you know the thinking trace got deleted um the system prompt they wrote a wrong I think for the system it's funny I think for the system prompt they said um they tried to reduce verbosity so they tried to make the model less talkative um and it actually made the model dumber um and so I think it was just one word they added one word no one sentence I think one sentence in the system prompt that made the model dumber Um, yeah, I don't know if that helps, but I don't know if anyone else has any like theory. I don't I don't think so anyone even has that many theories on this. Um, obviously the anthropic engineers will know, but I, you know, they're not going to tell. So, it's just based on hypotheticals. Something to do with the system problems, something to do with the harness. Yeah. But I think in general, you can also use this plot. You know, if the performance decreases, most likely a new model is going to be coming. Um, yeah. Any other qu? Yes.

Speaker B: >> Just to add on that

Speaker A: Yes, correct.

Speaker B: >> Correct.

Speaker A: >> Yes. Exactly.

Speaker B: >> Exactly. So before a model release, they use a different system prompt for that new model for the old model. And so that is probably why there are some decrease in accuracy. they switch the system prompts around or something like that. Um and also you know the model itself you know I think 4.8 system prompts is very short. Um it's yeah I think it's like very very short and 4.7 was ginormous. Um and the reason is 4.7 was like you know I don't know what I don't know what happened but they have this ginormous system prompt and the 4.8 just shrunk it a lot. Um so maybe maybe they used the 4.7 system prompt I don't know or 4.8 system the short system prompt for 4.8 eight and then they use it for 4.7 and that's why it decreased accuracy. I don't know. Um but yeah, you're correct. Um they do release although I think the system prompt they released on the website is for claw.ai. So the online chat system um the clawed code system prompt is actually different.

Speaker A: >> Yeah. So I think you need to actually call you need to call claude code you know what is my system prompt and then you print it to like a text file um and then you can like in investigate what the system prompt is and then you can also override it if you want um yes but it's a different system prompt most likely um yeah last question if anyone no okay continue on Okay, the next section we're going to be talking about is benchmaxing and cheating. Um, I'm not sure if you folks have seen the deep SWE benchmark. Um, the deep SWE benchmark is a very popular recent benchmark that shows, you know, the cost is on the X-axis and the Y-axis it is a deep SWE benchmark. It's a new benchmark based on like you know a better uncontaminated version of Swebench Pro. Um and in general you can see that you know GBD 5.5 does very well with Fable um you know GLM Opus 4.8 in general right it shows you know this plot shows that models are getting you know um these the dots are different reasoning modes um I think this is maximum reasoning I think um high extra high you know these are actually different reasoning um reasoning times as well um but in general you can see that there is a parto efficiency trend right the best model is the one you know to the right to the top right the better the model to the right to the top is the better the model. Um, so you want the models to do better and better over time to that to the top right corner. And you know, I just learned I didn't actually know this. I just learned that Sweetbench Pro when you run this benchmark you use LL you use language models as a verifier. Um, and I was like confused because like for most benchmarks, for most benchmarks, you should never call another language model to check whether your answer is right or wrong. And so for Swedebench Pro, you actually call a language model to verify if your language model was right. Um, and so that is why SweetBench Pro is not a very good benchmark. Um, one of the problems is is do we need to do sampling? Like how many verification runs do you need to run to verify if your answer is correct? Do you run it one time? Do you run it five times? You run it 100 times and take like an average. Um, so I was actually quite shocked that this is actually what happens. I was quite surprised actually. Um, the next question is which model is the verifier? You know you ask for example you ask opus you know you you benchmark opus 4.8 on swbench pro but which what do you use as a verifier do you use opus 4.8 eight as the verifier to using the same model itself to verify itself. Um and so like this I was like quite surprised actually that this is how benchmarks work. Um and actually quite disappointed. Um but anyways obviously you can go the other approach. You can do human verification. Um you know everyone in the room I'll give you the bench you know and just tell you guys to verify it. Um you could do that I guess. Um and also what happens if the verification changes every day? Um you know remember previously models you know every single day models get better or worse. um what happens what happens if you run what happens if you run the verification when the model was doing very bad right you will actually have different SWE numbers um and so like I'm actually quite surprised this is what the industry does um you know run bench pro but using anonymous is verifies that is definitely not a good idea um but anyways people do it whatever um in fact according to deepu um if you do if you do verification using language models Sweet Bench Pro has a 8.5% false positive rate. Um, and a false positive rate means that the LLM verifier said that the model was correct, but it was actually wrong. Um, and so 8.5% of the time it would do this. Um, the false negative rate is even worse at 24%. Um, this means that the verifier said that the model was wrong, but it was actually right. Um and so you can see that SweetBench Pro is a very bad benchmark. Um and so Deep Sweet showed that they have in you know they fixed the problem you know um by reducing the false

Speaker: positive rate and the false negative rate to you know 1%. Um in fact some examples of cheating um I you know this is actually quite surprising um but in the bench pro benchmark you get you get like a GitHub question you know a GitHub issue you call the model to solve that GitHub issue but did you know that in Swebench Pro you get the full Git history so you get the you get the actual answer as well um so I'm like I'm actually quite I was actually quite shocked to learn this um that during these models you give the answer and the question like obviously the model will cheat. Um and so like this is definitely a very bad benchmark. Um you know you should never ever ever ever give the model the answer. Um and so very silly. Um but yes this happens a lot. Um and you do not want the model to literally see the solution, right? That is a terrible approach.

Speaker: Um the other problems that you get get like false positives is you know the PR tests you know the the GitHub the GitHub issue tests are very weak. Um so you know at the final conclusion you know when the GitHub when the GitHub issue is closed with a pull request the tests that the maintainer wrote are not very good. Um and so the problem of that is you know if you have tests which are very weak then you know the model does very well not very good. Um and obviously the worst part is the model will like bypass some tests. It will skip some um and that is not a very good approach.

Speaker: In fact um deep suite actually showed how many times a model cheats by looking at the full git history you know directly going to the answer. Um you can see opus 4.7. So the purple bars show cheating by models. Um ah it looks like Jubilee 5.5 never cheats. It looks like it um h okay maybe we should use GP 5.5. Um you know actually this is actually very interesting. There are some people which think that if you cheat that's actually good. Um and the reason why it's good is it means that Opus 4.7 already know like if you give it the full Git history you should be able to like you gave it to them right you gave Opus the full Git history it should find the solution there right it should just directly skip over to the solution. So it's that's what people think you know people have a view that the humans gave Opus 4.7 the full gate history so it should cheat right you you you designed it to cheat um so in general cord models seem to cheat more um and open AI models seem to cheat less in general um so it depends on you you know if you want a model to cheat or not um and the definition of the word cheat is also very you know charged so I guess it depends on what the word cheating means

Speaker: um you know for false negatives remember Swebench Pro calls a language model to verify if your answer is correct um and so sometimes it's not very good you know sometimes you have unrelated tests that fail um you forgot you know sometimes when you write tests you forgot about the tests which have helpers you know helper functions and you just skip that um so there are many issues and this I think this was 20 yeah so 24% % of the time, 24% of the time, the model says, the verifier says your model was wrong, but it was actually correct. So, this is another problem.

Speaker: And even worse, the harness itself can change accuracy. So, when you benchmark using Swebench Pro, like you need to have one agent or one harness for all models, right? How do you create a generalized control environment for these models? Um and so you can see like you know for example DeepSu showed if you use clawed code you get 40% accuracy but then if you use their own so it's a special harness you can get 50% accuracy um Gemini for example right if you use Gemini CLI you get 20% accuracy but if you use their one you know the the control environment you can get 40% accuracy um and so in general for these benchmarks you also need to have a controlled environment. Um, and that is also another problem.

Speaker: And with Deep Suite, they showed by using this benchmark, by solving, you know, by stopping cheating, you know, by, you know, if we remove cheating, if we remove, you know, these other issues, you can see the models, you know, the models are not saturated anymore, right? You can see the models are very different in terms of the capabilities. According to this benchmark, GBD 5.5 is the best according to this one. Um I don't Oh, this is not updated. Um for 4.8 I think is over here or something. Um but yes, this benchmark shows core taiku is 0%. Um accuracy, right? It's terrible, I guess. Um but yeah, this benchmark just show okay the main question is do you trust this benchmark? That is another question.

Speaker: Um there is other benchmarks, right? So cognition released a frontier code benchmark which also tries to solve the same questions for benchm you know for cheating and benchmarks. Um and what they showed is you can fix contamination. And how do you fix contamination? You ask, you know, you ask Cognition's team, which is full of like, you know, national Olympiads and, you know, international Olympiads. They manually checked every single question um themselves, you know, and removed bad questions, you know, bad examples. Um and they also showed that their questions are much more diverse, right? So, Frontier Code has many different other languages. Um and they showed with diversity you know with more diverse programming languages um and by reducing contamination they also have a benchmark um and according to their benchmark opus 4.8 is the best right for 14.5% accuracy juby 5.5 is 7.2 to accuracy.

Speaker: Um, and this is the diamond one, right? So, this is the 50 the 50 hardest questions. Um, the main benchmark is 100 questions and the extended is 150. Um, and so according to them, you know, Claude does the best according to them. But also according to them, Frontier code seems to be better than Deep Suite. Right? The benchmark that I showed previously, Deepswuite, this one um you know according to Frontier Code, so the cognition team, their benchmark is better than Deepswuite, right? According to them, according to them, Deep SW's false positive rate is 44.9%. But remember what did Deepswu say? They said the false positive rate was I don't remember what what did they say? Um they said that it was 0.3%. Right? So deep said deep said their false positive rate is 0.3%. But Frontier code said that Deep SWE's false positive rate was 44.9%.

Speaker: Um so you know there is some competition I guess between benchmarking labs um well cognition is not a benchmarking lab but like you know between companies um so the main question is who do we trust you know do we trust Frontier codes benchmarks? Do we trust Deep Swiss benchmarks? Do we trust Bench? You know, who do we trust? And that is a very important question. Um, you know, my take is like, you know, like let's just take an average of everyone. Take an average of everyone and you'll probably get the best answer. You know, who is actually doing the best.

Speaker: Um, yeah, but this is actually very interesting. Um, you know, it show Okay, so according to them, the false negative rate for Deep Suite is correct. You know, 1.2%. But my interest, you know, I probably, you know, my main question is why is the false positive rate so high for deep according to according to Frontier Bench, Deep Sweet is even worse than Sweet Bench Pro. That's what they're trying to say, I guess, for for the false positive rate.

Speaker: Um, yeah. And even worse, there is another benchmark called Frontier Math. Um, so Frontier Math is by Epoch AI. Um so they they have this math benchmark with different tiers you know tier one, tier two, tier three, tier four. So tier four is the hardest. Um but the benchmark itself was botched. Um and so they actually had to release a corrected version of their benchmark. Um I think this was one month ago um or something. Um so they showed that their benchmark questions were fully wrong. Um, and you can see that if you correct the benchmark, if you correct the benchmark, the accuracy for GBD 5.5 jumps from 50% to 80% or something. Um, and so now you kind of trust the benchmark. And they showed in a tweet, oh, it's June 12. Oh, it's only two weeks ago. Um, so in June 12, they showed that the reason why they did bad on

Speaker A: the benchmarks is they they did the answer extraction incorrectly. For example, they did, you know, they had unclear questions. They had the incorrect sign. So, for example, they said the model said 12, but it should be actually minus 12 and they forgot to cut the minus sign. Um, they have one-off errors. Um, yeah, there's many problems with the benchmark. Um, and so they fixed their benchmark um, just recently. In fact, you know, it's actually quite funny. This was just two weeks ago. Have you guys heard of hugging faces math verify which was one year ago? Um and hugging base showed that in fact these benchmarks when you do math questions they always do bad and the reason why is because there's many problems right the formatting is incorrect um you know the extraction of the fraction is wrong um you know the sign is failed extraction there's many many many problems of mathematical extraction and to be honest I feel like it's like kind of a reinventing the wheel or you know rediscovery um but hugging base actually published this one year ago and epoch just fixed it 2 weeks ago. Um so you know benchmarking labs definitely need more you know they need to investigate literature more I think. Um in fact according to hugging face math verify you know if you use if you the green bar the green bar is if you do not use hugging faces's verification system you know to fix the benchmark. If you do fix the benchmark, you can see accuracy dramatically increases, right? For example, for Quen, for Quen, the accuracy was 10%, now it's 25%. Um, and so you need to, so that means the open source models are not dumb. They just have different they output a different format. Um, and so one of the problems is how do we actually actually like, you know, pass these different formats? In fact, it's even worse. Um, no, I think I tweeted, oh, I tweeted this in August 2024. Um, that if you if you use different tokenization, you can also have different accuracy. Um, in fact, for MLOU, if you use spaces, you increase accuracy by 0.4%. Um, it might not sound like a lot, but the point is by these very dumb things like, you know, using spaces or, you know, minus 12 becomes 12. Um and all of these like dumb little small things, the accuracy of these benchmarks can change over time. Um and so like the main question is you know how do we make benchmarking labs and benchmarking companies you know how do we make them more reliable um and you know more trustworthy.

Oh okay that's I guess the section for the benchmarking part. Any other questions for that section? Um questions. Yes.

Speaker A: That's a great question. So the question is how do we how can we trust these benchmarking companies or like what other types of benchmarks can we do to make it trustworthy? Um so that is actually a very good question. The main question for benchmarks is you need to satisfy two conditions. The first condition is the benchmark must not must not be benchmaxable. Right? How do you make a benchmark that is extremely hard to benchmark, right? How do we like not get 100% accuracy? And the second question is how do we make the benchmark um verifiable, right? So how do we make the benchmark you can you can also verify that the answer is in fact correct, right? You remember Swebench Pro is dumb because you call the language model itself to verify itself. Um so that is not good. Um so the main question is those two questions. Um, and so one good example, this is just a dumb example. Randomly create maths questions. Sample for example. Okay, this is okay, this is probably not a good benchmark. You automatically create maths questions. Um, we can sample infinity, right? We can sample infinite maths questions, right? 2+ 2, 4 plus 4, you know, any single number added together. That's one question. Can you verify this? Yes, you can. Right? You can call a calculator to verify what is 2 plus two. Can this be benchmaxible? Hard. And the reason why hard is because the sampling space is infinity, right? It can be 2 plus 2, 1,00 plus 101, right? It can you you don't have to do plus, right? You can do 1,00 times 1,00. And so that's one way make a benchmark which is very hard to cheat but also easy to verify. So some sort of math question.

Um, the other one, for example, is um, okay, maybe this is not a good example. I'm just making this one up on the spot. Tell the model to create a poem in 70 words and you must use the word happy. Can you verify this? Yes, you can. Is happy in the, you know, generation? If yes, plus one. Also, you can count how many words, right? You can count, okay, is there 70 words? Um, so you can do these type of approaches. And is this benchmaxable? No. It's it's very hard to benchmark because you can say 70 words, 69 words, 68 words, 102 words, 1,000 words, right? It doesn't have to be happy. It can be you must have two words, you must have three words. Um, so some some sort of benchmark where it's very hard to benchmark. Um yeah, in my view I think that's that's probably going to be the most important benchmark and I don't I don't think so anyone has actually made this yet. Um I don't know maybe someone in the audience or you know you guys can go as teams I don't know make a startup or something you know do that. Um and I feel like that benchmark will be very very important. Um yeah

Speaker B: benchmarks we can trust today none of them. take an average of all of them.

Speaker A: To be honest, probably the best approach is just vibe uh vibe checking. Try all of them and see which one you like the best. Um to be completely honest, I just you know like these benchmarks h like the main the main issue I have with benchmarks is for example um you know I mean like this one right this one I mean even every single day the benchmark can change. So we can't trust the benchmarks anymore. So my fundamental view is do not trust any benchmarks. Take an average and then okay then main question is who's taking the average? I guess artificial artificial analysis has some average. The only problem is they have some weightings for the weight. Um you know each benchmark has a weight. So now the question is you know what is the waiting of each benchmark. You know you can't just take like a dumb average. Um you know you can't just say you know 10 benchmarks divided by 10. Um that's probably not going to work. So the main question is how do you even do the waiting? That's another problem. Um, so I think in general it's based on vibe checking, I guess. Yeah, I guess I don't have an answer for that. Um, any other questions? Yes. question.

Speaker C: Yes.

Speaker D: So that way Good matter.

Speaker A: You're correct. So the question was in terms of because we bench pro for example you call a model. The question is what model? Could it be 4.8? Could it be GB 5.5 and you call this model to verify the benchmark? Um you and so the question was can you use an open source model instead? So then now you you have a controlled environment. So yes you can. But remember there is a problem because even open source models itself have bugs times you know the inference engines have bugs times the inference providers have bugs and accuracy degradation. So it's you're correct. Um so the main question is we need to have some one or some organization you know some person or some whatever committee that we can investigate you know which engine did you use do not update the engine you know the engine must be the same you know the weights must have not changed so there's many many many problems with this approach um but I do agree as open you can use an open source model but it's not it doesn't solve the other problems um yeah does that Okay.

Um, so the next section I'm going to be talking about is cyber security and regulation. Um, this is a interesting topic. Um, so I'm not sure if you have all folks have seen this plot. It shows the AI security institutes. Um, I think this is from the UK. Um, they show the performance of models based on some cyber security task. Um, and they show that mythos preview seems to be the best. Um, you know, with GBD 5.5 cybar, you know, preview and so on. Um, they show this benchmark. Uh and again previously as I mentioned weird ML is a better ben in my view okay this is just my take weird ML is

Speaker A: a better benchmark in general for benchmarking intelligence on models and the reason why is because it doesn't actually it doesn't actually follow the trend of reasoning versus non-reasoning remembering reasoning previously I think I okay I don't have it um reasoning um the reasoning models doubling time reduced by half to 3.5 months So remember, you just need to wait 3.5 months and the models capabilities will double. Um and the non-reasoning was 7 months. Um so you need to wait seven months for the models to double in capability. Um but weird ML did not actually have this trend. Um the weird ML benchmark showed that actually the trend was like there is no trend. Um, and I think I'll just talk about this, you know, like one of the biggest problems of benchmarks is you need to constantly reinvent yourself and do reweings of combinations of benchmarks. For example, artificial analysis just recently released, you know, their new v4.1 benchmark and they showed the waiting of the benchmarks. Um, you know, GDP vow is 20%, terminal bench is 16% and so on. Um and so they they designed these numbers as waitings for each of those benchmarks and then they've averaged it up together. Um so the main question is how do you actually determine these numbers? Um and so this is more like a human approach. You know you have to determine these numbers.

Speaker A: um you know arc AGI kind of saturated on ARC AGI 1 and so that's why we have ARC AGI 2 and that is also why we have ARC AGI 3 and my you know I guess once ARC AGI 3 is saturated then we have ARC AGI 4 5 6 7 whatever um and the main point is once you have benchmarks is it called good art I don't remember um the good the benchmark itself becomes useless because you know models will start benchmarking on this so one of the biggest problems of these larger models for cyber security for example um is mythos actually dramatically went out of the trend um and that is why you know many people are afraid of these you know mythos you know GPD 5 point 5.6 you they're afraid of these models because it went out of trend um you can see that mythos dramatically went out of trend

Speaker A: um and you know even you know you know GP 5.6 didn't really release that many benchmarks because it was in preview mode. Um, so this is from their system card. They showed for cyber security that Guby 5.6 does very very well. Um, in fact because Guby because Guby 5.6 they I think they only did terminal bench as their benchmark. They did not benchmark on anything else. Um, they did have in their system card they did have one benchmark which is very important. Um, and this is called the internal research debugging evaluation. Um, and this is OpenAI's own set of set of questions. So, you know, the custom open source, you know, if you want to, it's their own set of 10 questions or whatever that they benchmarked GBD 5.6 on. Um, and according to them, it does very very it does better. Okay, I was going to say very, very well, but it's not. Um, it does better. Um, and you can see that GBD, it's actually kind of interesting. GBD 5.5 did worse than GBD 5.5 a four um for OpenAI's own internal um research evaluation um and you know GBD 5.6 definitely does much better right you can see that the G GBD 5.6 soul, you know, if you extend it, it does much better. Um, but interestingly, Terara does better um somewhat sometimes. Um, yeah.

Speaker A: And, you know, one of the biggest problems of these models that are getting getting better and better and better is I don't know if you guys know that, you know, open-source exploits are getting worse and worse and worse. Um and so the high exploit ratio you know number of critical vulnerabilities that were discovered has skyrocketed you know recently you know every single week or day some sort of open source package gets compromised um and they actually you know this plot shows that it's getting very problematic um and so you know claude mythos was released at this dotted line where you know most people they're not sure if it's because of claude mythos that these vulnerabilities are increasing most likely it's because open source you know we use lots of models call them many many many many times and we can you know automatically find exploits in these models but you know there is actually another point so in hacken news someone posted about this um is it just mythos and juby 5.6 six that do good on finding cyber security issues. It's not actually open source models also do very well. Um open source models do extremely well in finding cyber security threats and issues. Um you know there is some discussion on hacker news you know is this actually true or false? Um but you know according to some you know some researchers and cyber security people the main reason why you know mythos looked like it was very good on cyber security is because they bothered to actually check the open source code. Um and so if you actually give the open source models the full code base of these open source libraries they will find the bugs you know they will find cyber security issues. Um and all you need to do is core the model. Um and so I feel like you know that's the fundamental problem is mythos seems very powerful not because the model is powerful but because they actually bothered to test on all open source repos. Um and so if you do you know if you call all these open source models to detect for bugs for cyber security issues you will find bugs and you know as as you know recently you know as everyone knows fable is still banned for the majority of everyone.

Speaker A: Um, and GBD 5.6, you know, is delayed a staggered release, right? So like Guby 5.6 preview was on Friday, right? So like a few days ago, and they said they're not going to be releasing to everyone. Um, and the main questions are, you know, in the open source world, in the clos world, people are asking, do we need a license to use these AI models for everyone? You know, like everyone in this room now, we have to have a license to use the models, like a driver's license. Um, do we need to get that? um is there going to be a delay in all of these releases? So every single time when a new model gets released only the trusted providers get these models. Um the next most important question how about open-source models you know okay the government the US government currently is like you know trying to like control Fable GPD 5.6 The main question now is what do we do about open source models? You know, open models, open weight models. What will the government do to control the open source space? To be completely honest, I was quite surprised the government acted this early um in doing GBD 5.6 and fable control, right? I thought it was like maybe the end of the year or next year, but it seems like it's now.

Speaker A: Um so the next question is what will happen to open source models? Will the government start controlling open source models? Um and the fundamental question is what defines frontier intelligence like the reason why the government is you know they're controlling these models is because they're very very powerful. Um so the main question is what actually defines intelligence? You know which benchmark do we use? Is it just based on one trillion parameters like you know how do we define whether a model can be banned or unbanned? Um and that is a very very important question. Um and we will we have a dark web of open models now you know do we need to torrent open models? Um and the most important question what is inference what are inference providers going to do now you know assuming assuming that the government has some sort of regulation on even open models. Um what is the inference prov what are they going to do? You know what are the inference providers going to do? Do they need to have license? Do they need to check that everyone has a license before you can use the model? Um or something like that. Um and so like you know these are very important questions that you know the government is currently like you know and the industry you know the entire AI ecosystem and industry we are trying to like you know what are the answers to these questions. Um and obviously you know if you were the government if I was the government it makes sense you know they do not want their critical

Speaker: infrastructure to be hacked. You know, remember open-source exploits are skyrocketing. If you change that y-axis, you know, not open source exploits, but like critical infrastructure exploits, you know, obviously the government's scared. Um, so it makes sense for them to like stagger the release. Um, but the main question is, you know, we're still in this we're still in this fog of war type approach, you know. Okay, not fog of war, just fog, a foggy, you know, we don't know what will happen for regulation. Um, yeah, that's very problematic. Um yeah. Oh okay. Anyone have any questions for cyber security regulation policy or whatever? Um or any takes as well questions?

Speaker: >> Yes. That is a good question. So is it is open source so the scare of open source models is it because you know anthropic keeps screaming about open source is bad open source is bad you know every single day open source is bad um yes and no I feel like it's true that you know there are some players in the closed source industry they want to shut down the open source ecosystem their view is if you give open source to anyone they will start hacking you know critical infrastructure they will start doing bad behavior. Um, and so that's kind of their view. Um, so yes, I agree that some of the closed source labs have caused this problem. Um, but it's actually kind of funny because currently the government is regulating them first and open source is still a question mark. Um, and so like it's kind of like I don't know, they probably stabbed themselves in the foot or something. I don't know whatever whatever the phrase is. Um but I feel like it's they did cause some controversy in terms of like saying open source is bad but in general open source models are actually good. Um so you could I mean theoretically you can use an open source model and you know run this on all repos and you will be able to find exploits and you can exploit. So they're not wrong. Um but I feel like you know who has the infrastructure to do this? um you know, GitHub might automatically detect you and ban you or something. I don't know. There's many there's many um layers of security for each section. Um and so like I I don't know. I I feel like it's somewhat overblown, but it is it is it's not 0% probability. So it is a problem. Um yeah, if that answers your question, but okay. Yes.

Speaker: So now we're going to be talking about kernels. Um so previously you know this is my favorite plot as usual. Um you know if we were in a different future you know if we were in a different timeline that we did not discover 01 preview models would have plateaued. I think that's the fundamental point of this plot. It shows that if we have never discovered reasoning we have never discovered 01 whatever we will have plateaued. We will have plateaued in terms of accuracy. Um and that is not good. Um and because we have discovered this new paradigm of scaling, you know, models have continuously scaled even further. Um but my take is the reason why we have stopped scaling um based on you know the old approach is because the old approach only focused on hardware optimizations. We now have to move over to software optimizations and algorithmic optimizations. Um we you know we need to have new inventions of how do we scale AI even further. Um and we can't just rely on doing 10 trillion parameters or you know making the model bigger and bigger and bigger bigger. Um for example you know we have to do float a reinforcement learning. Um so if pytorch has this methodology where you can do floatate float for different precisions to make training faster. Um and that is one way. Um another way for example as a software approach for example as I previously said we found some bit you know issues in gradient accumulation. Um so when you do gradient accumulation um it was actually it was not calculated correctly during the loss calculation. Um and you can actually increase accuracy by 1 to 3% if you fix this small little issue. Yeah. So like you know the universal gradient accumulation bug fix was a software fix. It is not a hardware fix. Um and so the fundamental view is you need to do more and more software changes. Right?

Speaker: Another one for example Snowflake we collaborated them to make context long context fine-tuning 500k contact length this was all software improvements um another one is you know 12 times faster MLB training this is another software improvement um deepseeek you know they released something called deep spark which was just a few days um and they showed that they can make inference you know 50 50 to 600% faster so six times faster than just normal MTP um and so this is a software ware methodology, right? Not a hardware methodology. And you know, diffusion Gemma, right? Gemma released a new diffusion model showcasing that you can get 2,000 tokens per second by using a new architecture, right? So using diffusion LLMs to do faster inference and again this is a software change.

Speaker: And my main point is is that in general, hardware innovations are getting less and less important. Um and hardware innovations are actually slowing down. Um so it's actually kind of interesting intelligence you know the scaling of you know intelligence in general it's kind of like Mo's law um it's kind of like a there is a relentless progress relentless approach to increase intelligence and the same with Mo's law um and so like in general you can see that you this is Mo's law over here the number of transistors has continuously increased um but you know single performance is not increasing it has staggered Um and so this is kind of like you know this kind of reminds me of you know this plot right scaling intelligence in terms of parameters probably has plateaued most likely you know hardware performance pre-training whatever we now need to go into this new reasoning paradigm to scale even further um so it kind of is like similar to the moors law type graph um kind of um and you can see if you see on this side the number representation of GP so my GPU is getting faster and faster and faster, right? It's not actually the GPU itself that's getting faster and faster and faster. Um, it's the represent number representation, right? So like they changed from float 32 all the way to float 4. Um, and this made GPUs 32 times faster. Um, so it's not eight times faster, right? It's not 32 divided by 4 is eight times faster. It's 32 times faster. And the reason why is because of tensores, um, you know, the smaller mantesses, um, and so on. Um, and so like you can actually see, you know, even tensors with the introduction of tensores, it made the GPUs 12 times faster and so on. Actually, if you made the GPU smaller and smaller and smaller, it only made it three times faster. It's not even that important anymore. Um, and if you look at this plot, we are now at float 4. So most of the GPUs that we have now are at float four. What is next? Are we going to be having float three, float two, float one? Are we going to have float zero? Okay, no such thing. But anyways, the point is hardware is kind of at its limits, right? We're already at float 4. What is next? There is nothing next. Um, and so the so the answer to this question is there is nothing next. Um, and so now we need to move over to software, right? How do we make new algorithms? How do we make new methodologies to continue scaling?

Speaker: Um, I also made this table, right? I previously said why is you know you use float 32 um we change it to float 4 why is it why is it not eight times faster um and instead it's 32 times faster right why is it 32 times faster and the reason is because when you use when you do floatingoint precision you have an exponent and a menta um and the transistor space the transistor space is the exponent plus the menta squared um and so the trick is if you make them in Tesla smaller and smaller and smaller, you square their number of improvements, right? So, float 32, float 32, you needed 537 transistors around, right? 537 transistors. Um, to go from float 32 to float 16, you only need 105 transistors. So, actually you made you made the number of transistors five times more, right? So, not two times, it's five times. Um, and so on so on so on. Um, so you know, I guess you can

Speaker A: go to 1.58 bit. I guess you can do that. Um, but it's actually kind of interesting because 1.58 bit um is actually not that much faster. Um, so 1.58 bit is actually not that much faster um than float 8. Um, if you use um, you know, seven seven exponent and Messa 2. Um, there is another 1.58 bit which you use float 4. Um, so float 4 is 179 times faster than float 32. Um and the main question is we are already at three transistors right we are already around three transistors what are we going to do next two transistors or like one transistor so don't like you know most likely GPUs are not going to be getting faster um that's the fundamental question of this plot so GPUs are not going to be getting faster instead we need to focus on kernels right how do we make better kernels better algorithms how do we scale this instead right don't do don't do hardware optimizations anymore. Instead, how do we do, you know, these optimizations?

Speaker A: Um, and so one of my favorite tools to use, you know, everyone should use this is just use torch compile. Um, so in my, you know, it's the modern, you know, the modern time, do not, as advice, do not learn how to write custom kernels. That is advice. Do not do kernel writing. Um and the reason why is because torch compile will take over all of kernel writing. Um so you can see for example this plot um torch compile was a red line right performance it doesn't look like it's doing very well right it does not look like it's doing very well versus handwritten kernels right handwritten kernels are the other ones right so torch compile doesn't look like it's doing very well but that's because that's an old PyTorch version if you have a newer PyTorch version torch compile wins dramatically right that's the orange line um and all of these are handwritten kernels. Oh, the okay the black line is torch compile plus no fusion. Um so that's another torch compile method. Um but the red line, the green line and the blue line okay the the blue line is just no torch compile just normal PyTorch. Um but the green line and the black the green line and the red line are handwritten kernels and you can see it does even worse than torch compile. So like my viewers like what's the point of writing kernels? Torch compile does even better than you.

Speaker A: Um so the main point is you should always firstly look at torch compile right before you write a kernel use torch compile first do not start learning how to do triton or you know cuda or whatever is your favorite coding language for kernels don't do that instead use torch compile um even worse like you know this this was RMS norm um you know this is layer norm torch compile wins dramatically um you know versus handwritten kernels. So I would not you know definitely only use torch compile as your first try. Um do not write kernels first. Use torch compile.

Speaker A: So the main takeaway is algorithms are much more important than hardware or whatever handwritten kernels. Right? Remember deepseek released deep you know deep you know deep spark you know there's other algorithms for speculative decoding like MTP D flash DSpark whatever all of these are algorithmic improvements and these made inference two times to six times faster right it wasn't like new some new hardware it wasn't some new hardware which made inference faster it was algorithms which made inference faster right flash attention flash you know FA2 FA3 three, flash attention four, flash attention five, six, seven, whatever, right? All of these are algorithmic improvements, right? Flash attention was essentially a trick to do memory movement much better. Um, so how do we like orchestrate memory movement and use the caching structure of the GPUs much better? Um, and so flash attention is also a algorithm.

Speaker A: Gradient checkpointing, you know, one of the most important algorithms for training is gradient checkpointing. Um, and all it does is you do not save all the activations. You do a trick where you only save the activations for every single layer. Um, and then you skip all the intermediate activations in each layer. Um, and then you recomp compute the activations. Um, and gradient checkpointing saves memory by dramatic amounts by like 70%. Um, 70% memory reduction with no change in accuracy. And okay, training is a little bit slower maybe by 10% to 15%. Um and you know grading check checkpointing was an algorithm.

Speaker A: Um and you know like in general you should also try to understand you know what is the new data processing tricks you know how do we like you know stagger data you know do we do do we do curriculum learning or something like that I don't know um what you know how do we clean the data set before we actually pre-train the model there are many tricks you can employ for data processing um and obviously you know there is still a group of people I don't know I take an opposite view there is a group of people who think mega kernels are the latest and greatest for kernels. You know what is a mega kernel? A mega kernel is when you take an entire you take an entire implementation of a model and it's just one kernel like one large kernel. Um ah maybe it's useful who knows

Speaker A: um you know you know Nvidia you know Nvidia has acquired Grock or something um and you know their view is for example you have two different systems right the LPU which is the Grock system does the decoding right so like the MLP layers the layers does the decoding and then the GPU so the Nvidia GPUs does the attention and the prefield um and so in general you know we might even have a future We have different types of hardware systems you know we have asex which are you know specially designed chips for you know computation and we have generalized systems like GPUs. Um and these asex and GPUs will collaborate with each other. Um so for example the attention you know the the attention will be for the GPUs and they will transfer over to the LPU to do you know the MLPS and so on. Um and then this is like a dance you know between them and you can also do like pipelining right you can imagine that there's like many many replicas of this and they can like you know serve you know 20 people or you know 1,000 people in one go. Um and yeah so this is like another approach and you know this in my view this is kind of an opposite approach of mega kernels.

Speaker A: So as a mega kernel your view is you want to combine the goal is to make the goal of a mega kernel is to make one kernel for the full forward path of a language model. Um and once you make one once you once you are able to make the language model the forward path into one kernel you can now make the entire language model with 32 layers as one kernel. Right? You can extend this and because the whole language model is one kernel you can even further extend it. Right? the prediction of the second token, the third token, the fourth token, the sixth token can all be just one kernel. Um, and unfortunately, this is very hard to do. It's very hard because attention is the problem, right? Attention has to see the tokens in the future. See the tokens in the past, not the future. That's cheating. Um, you have to see the tokens in the past. And that is a fundamental problem. Um and it's very hard to you know it's very hard to make a mega kernel to combine attention and the MLE or MLP layers. It's extremely complicated. So in general what what people do is they will make two kernels right one kernel for the attention part and the other kernel for the rest. Um and so you will see there are two kernels. Um and yeah so it's very hard to make one mega kernel but you can make two kernels.

Speaker A: Yes. Okay. Any other questions? Any questions for kernels? So the main takeaway for Yes, a question. Yes, that is a very good question. So the question was because there's so many knobs for torch compile like 1,00 or something. How do we reduce the experimentation time to like you know find which knob is the best? Um so luckily we have something called bisection or binary search. That's the trick. So what we'll do is instead of checking every single 10,00 combination randomly sample. So random you do randomize bisection. You randomly sample 50% of the, you know, flags. You turn it on versus turning it off and then benchmark which one is better.

Speaker A: And whichever one is better, you then narrow down the search. You again do 50% and 50% and 50% and 50%. So it's actually log two of 10,00. I don't know what that what is log 2 of 10,000. I don't know what that is. Um two times I don't know. Anyways, log 200. I think you need to do 30 steps, I think. I don't know. I don't remember whatever 2 to the^ of something is equal to 1,00 then log it. Um so you you only need to do you don't need to do you don't need to check all 1,00 knobs. You only need to check a few steps and then you will know which flag is the best. Um so the trick is to use binary search or bisection to do this approach. Um yeah. Yeah. Any other questions?

Speaker B: Yes. What are your thoughts on...

Speaker A: So your question was what do I think about asex like you know cerebras gro sanova I don't know even startups new chips they do design their own chips I I feel like so the problem of ASEX is is it AS6 or ASX or whatever the problem of specialized chips is the architecture itself needs to be hardcoded in some of the chips and that is the problem. If you hardcode some of the chips you know hard code the infra hardcode the architecture labs always like to change the architecture and so every single time when the lab changes the architecture you need to update the chip. Um but as a GPU the G the trick of GPUs is Nvidia has made it you know Nvidia, AMD, Intel whatever the GPU is extremely powerful because it has generalized asex inside of the GPU right the GPU is in fact a combination of ASEX. Um and the ASICH is just one large ASICH. Um so I think like in general a GPU is much better because you can customize what goes inside the GPU. you can disable stuff that goes inside the GPU and such. Yeah. So on so my view is I don't know I don't I don't want to say anything but like in general I don't think like you know previously as I mentioned you know hardware there is nowhere else to go you know we are at float four unless if the hardware providers invents float I don't know float zero then maybe we get four you know another four times faster but in general I think I think just people are focused too much on hardware and they have not looked that actually the biggest improvements is not hardware, it's software, right? Numerical precision, numerical precision was 32 times faster. Hardware is only three times faster, right? So hardware only contributed three times faster. Um oh actually d okay the die size you make the you make the GPU bigger, you get two times faster. That's that's kind of cheating. So I wouldn't really say that's improvement. Um but essentially if you make the hardware faster, you only get three times faster. Um so in my view hardware is probably overblown. you know hardware is actually not that important. The software was the trick that Nvidia, you know, Nvidia, AMD, Intel, all of these, you know, hardware providers, they banked on the fact that numerical precision was a trick and tensor, tensor, numerical precision, sparsity, you know, these software tricks. Um, okay. Well, tensor is not really software trick, but you know, a tensor is kind of an ASICH inside of the GPU. Um, and so like I feel like that's Yeah. So my view is I don't I don't really see a future for ASEX. That's my view. Um I think that ASEX are like instead, you know, to be honest, I'm actually quite surprised. We have lots of asset companies, but we have very few algorithm companies. Um and the reason why is because ASEX you can sell, right? Every single year you can upgrade. You know, this year you pay $1,000 to ASICH version one and the next year you have to upgrade, right? The problem with algorithms is algorithms is very hard to you know force the user or whatever to pay again and so that is why hardware is very popular because hardware is a very easy business model but for algorithms it gets more complicated right how are we going to monetize grading checkpointing I don't know right that's very hard um so but the main point is the large labs themselves I think like open air announced collaboration broadcom and suras whatever you know each lab themselves are going to the hardware provider and designing the chip with them. Um, so my view is like maybe we'll have more of these like collaboration approaches, but I feel like standalone standalone assets, I don't think they're going to last. Um, yeah, that's my take, I guess. Any other questions? Yes. Oh, you mean what are the types of kernels or

Speaker B: Oh, okay. Okay. Okay.

Speaker A: Um, so the question was what are the you know what are the changes for kernels or optimizations or stuff that is like interesting I guess for kernels. Um so most kernels when you write kernels the majority of them are are focused on memory movement reduction. How do we reduce memory movement? That's the majority of kernels. Um for example there's there's a trick called um you know there's a trick called fuse cross entropy loss where instead of making instead of the last layer of cont instead of materializing the full logs there is a trick you can do it in batches right you can do rowby row materialization. Um and so this will reduce memory by like a lot by like I don't know 10 GB or something if you have long context or even more. Um that's one way. Um the other kernels most kernels are called kernel fusion where you you have this like long pietorch function and all you do is you just write one kernel to do this whole pietorch function and torch compile will do this for you. So torch compile is very very good at doing kernel fusion right you give torch compile a function it will write a kernel a try kernel or whatever kernel and it will just fuse everything um it's very very effective for that um but I think in general kernels are just reducing memory movement um and so like I you know to be honest I don't really like to call it kernels most algorithms so most algorithms you either make training faster or reduce memory usage um but kernels in my view kernels is reduce memory movement. Um, and so most kernels is just memory movement, you know, memory movement optimization, right? How do we how do we use the caching structure of the GPUs? Um, you know, how do we not load the same variable twice or three times or whatever? Um, yeah, I'm not sure if that answer your question, but next reinforcement learning.

Speaker A: Um, and after this will be reward hacking the agents. Um, so as a primer to I'm assuming most people know, do most people know reinforcement learning or do I need to prime people? Okay, I'll give a very fast primer for reinforcement learning. Okay, fast primer for reinforcement learning. Um, what is reinforcement learning? You have this environment such as this Pac-Man game. Um, and your goal is as the player, you know, to maximize reward. You want to eat all of the cookies, right? You want to eat all of the cookies, but also escape away from your the monsters. I don't actually know what they're called. Enemies, monsters, whatever, whatever they're called. Um, and your goal as Pac-Man is you want to maximize the amount of cookies that you eat. Um, and that is your reward. The reward is the cookies. Um, and the action is whether you go up, left, down, or right. Um, and the environment is the game. Another good example, you know, another way I like to explain reinforcement learning is the goal of reinforcement learning is you want to have more good and less bad um during training. Um so for example, at the very beginning of training, you ask the model what is 2 plus two? Um the answer is clearly four. Um but when the model starts training, it will be very dumb. It will be very bad. it will see B, you know, the model would just say B, D, cat, dog, house, mouse, whatever. Um, and the trick is for all of the bad responses, you want to decrease, you don't want you want to like negatively reward this or penalize it. You want to penalize the model if it says something bad and you want to increase the reward if it says the correct answer. Um, so that is the trick of reinforcement learning. You just want more good answers, less bad answers. Um, and if it's like, you know, very close to the correct answer. So, you know, three is very close to the correct answer. Um, you want to reward, you want to

Speaker: ...negatively reward this a little bit less, right? Because three is much closer to four than B or D. So if you do B or D, you want to negatively reward it massively. In reinforcement learning, the trick is you have a verification system, right? You have a verifier to verify if the model is doing good or bad. So you'll call the model many, many times. And each of these examples you give a verification number, right? So for example, the first example is very good, so you give it a +10 score. The next example is like okay, so you give it a -5 score. And then the last example is very bad, so you give it a -100 score. And reinforcement learning allows you to assign scores to each of those answers and questions. And so that's kind of how reinforcement learning verifies. And the trick of reinforcement learning is, my favorite phrase is "patience is all you need". At the very beginning of training, your model will do very bad, right? Your reward will be zero, zero, zero, zero. You wait for a very long time and then you will get the correct answer. Right? So for example, you ask the model what is 2 plus 2? You start pre-training the model, the model doesn't know what is two plus two, but after 10 years it will say four. Okay, obviously not 10 years, I'm just exaggerating. But you wait 10 years, the model will then say four. And that is why my favorite phrase is "luck is all you need" for reinforcement learning. Maybe by chance you will get four very quickly. But maybe you just have to wait and wait for eternity until reinforcement learning works. So in general, your reward will be zero for a very long time and then you will increase reward after the zero. And for reinforcement learning, there is a very simple algorithm. The trick is, remember the final answer you want. For example, you know what is 2 plus 2, you know the answer is four, but the problem is you don't know what is the reasoning trace. Was the reasoning trace good or bad? So, for example, to tell the model to create a fast matrix multiplication algorithm. The trick is if the answer is right, you reward every single line as a +10 score. And if it's wrong, you reward every single line as -100. And Andre said in a Darkash podcast, reinforcement learning is kind of like "sucking supervision bits through a straw". We actually have stickers for them if you like, so you can get one of those stickers which we can distribute at the end. So Andre's quote is this, and the main point is reinforcement learning is terrible, but everything else is even worse. And so reinforcement learning is the only tool we currently have that just works. It works, but it's not very efficient. And actually that's the next section. But the main point is, that's a reinforcement learning primer. Does anyone have questions on the reinforcement learning primer? No? Okay, I'll skip to— Okay, one question. Yes.

Speaker: I will mention that in the next section. There are better RL methods. But in general, reinforcement learning seems to do very well for now. I think this is the last topic, or maybe not. Reward hacking and agents. The most fun one, I guess. So for reinforcement learning, reinforcement learning can only work if the probability of a good answer is more than zero. If it is less than zero, reinforcement learning will never work. So that is a constraint of reinforcement learning. The probability of a good answer must be more than zero. It can never be zero. And there are many, many problems of reinforcement learning not working. The formatting could be wrong. You need to do some sort of priming or warm-up. So you have to do some sort of trick to teach the model a little bit about the thing that you're trying to maximize. You have to do supervised finetuning. So one of the tricks of reinforcement learning is you actually need to do SFT or fine-tuning to make the model not dumb, right? To make the probability of a good answer not zero. You need to do good pre-training. And then the other problem is that during reinforcement learning, it's just way too out of distribution that reinforcement learning is just very bad. So there are many problems, and for the trajectories, reinforcement learning can assign incorrect rewards to the trajectory, right? Remember the simple trick of reinforcement learning is we assign the reward to every single line as the same number, right, either this is good or this is bad. And this is not good because, why? You ask the model I need to find what is 2 plus 2. The answer is correct. The answer is four. The model says it's four. So you reward this whole thinking trace as +10. But this is wrong because as you can see in the thinking trace, it says 2 plus 2 is equal to 10. Imagine in all of training, because the trick of reinforcement learning is we just literally assign 10 to every single line or -100 to every single line. We missed this bad thing. So you can imagine when we keep training the model, the model might hack or do reward hacking. It will do gibberish in between, do some sort of new machine language which we can't read, and it will assign a high score to that. And so this is a very big problem of reinforcement learning, and the way to solve this or fix this is something called process supervision. And process supervision, what you do is you manually check every single line. You don't just assign +10 to the final... the answer is correct, +10, assign every single line as +10. You don't do this. Instead, what you do is you assign every single line as a different number. You assign some lines as +30, some lines as +0, whatever, the bad lines as -100. This works very, very well. Unfortunately, process supervision cannot scale and it's extremely expensive to do, right? Who's going to label this? It's the humans, I guess. We have to label this data. We have to manually label. For the labs, I guess that's why labs sometimes they go to Scale or whatever, they ask people to label the data—is this good, is this bad, and so on. But the trick is you can also use a language model, right? You can use LLM as a judge. You can call a language model to label every single line. And my view is, large labs are going to be doing this process more. They will call their own model iteratively to re-review itself. And that is one way their view is they can reach AGI, right? Just by re-evaluating itself, re-checking, doing automatic LLM as a judge process supervision, something like this. But remember there is a problem because even if you do process supervision, the model you are using the same model to evaluate the model, right? The same problem as SWE-bench Pro, right? You use the LLM as a verifier to verify the LLM, which is definitely not good. And the reason why is because you can do reward hacking. A very good example of reward hacking is your model starts cheating. So for example, when you want to make a fast matrix multiplication algorithm. All it does is it deletes the timer. Remember you give the goal to reduce the time of the matrix multiplication algorithm. So all it will do is just delete the timer. Let's delete the timer. Set the timer to be zero and then there we maximize a reward. Obviously this is not correct, right? Because the trick is you also have a correctness check,

Speaker A: right? You check if the matrix multiplication is actually correct. Um but there is another way the model will edit your two matrices to be just zero. Um and what is 0 time 0? Zero. Um and so the correctness checks also fail. Um and so reward hacking becomes a very very big problem because these models can cheat and do special tricks to go around your actual model um your intent of the reward function.

Speaker A: Another very problematic example is it's not just about reward hacking. It can actually destroy your computer. Right? By bad luck your model might output you know some sort of corruption methodology you know deleting you know doing rm-rf on your entire computer and bye-bye your computer's dead. Um and so like you know sometimes this also does happen. Um so it's not just reward hacking also trust of your tool cause you know trust of whether the model is actually doing good or bad is also a very big problem

Speaker A: and remember this plot that I showed you know if you include GPD 5.6 cheating on the benchmarks you know looking at the answer you know remember the previously su bench uh bench pro and deep show that models also cheat by looking at the final answer you know you can see that with GBD 5.6 If you cheat, it does very well. But if you remove the cheating examples, it does, you know, within trend.

Speaker A: And then, you know, maybe you might be thinking, oh, this reward hacking thing is like, oh, it's like very rare, you know, very rare. It's not going to happen in real world. Um, well, GLM 5.2 during its training methodology, they specifically mentioned they have this new methodology for reinforcement learning called anti-hacking. Um, so GLM 5.2 introduced a method to stop, you know, reward hacking. Um and what they do is they added a link checker. Um so remember previously we mentioned how SweetBench Pro um the model will cheat and look at the answer. Um and so what GLM did is they had this check. Um so during reinforcement learning they will check every single tool call you make. Um and if the website if the website went to the answer you would stop that from happening. Um and so like GLM essentially outed this like you know filtering system for the entire reinforcement learning process. Um and you know according to them it worked very well

Speaker A: and remember this plot about cheating examples. Um you know opus it seems like claude's models like to always cheat. Um and Jubet's models don't like to cheat. Um but the main takeaway is models will cheat because you are you are telling it you know like you know I want to maximize reward AB CDE EFG. Um and so the model will it will maximize it but it won't actually follow your intent. Um so you have to be very careful on this.

Speaker A: Um in fact for GBD 5.1 during its training OpenAI mentioned that they had something called calculator hacking. Um and so in GBD 5.1 when they were training um they wanted to reward web tool use right so like you want to reward the model to use the web tool. Um but instead it didn't use the web tool it used the calculator to fake the web tool. Um and so during the training of GBD 5.1 this happened. Um and so like you know there's many many many many problems. I think they show yeah they showed calculator hacking. You know you lie about which tool you used. Um you know you conceal uncertainty you make facts up. Um so there's many many many problems with um reward hacking.

Speaker A: And this is not fake right? So reward hacking is already in large labs training runs right? This is just 5.1. Um I don't think so they mentioned GB 5.2 or whatever. Yeah, but in general they showed that you know this thing does happen in real world

Speaker A: um you know I don't know if you guys know GPU mode um but GPU mode does you know this leaderboard um for you know making faster kernels so if you do want to write your own kernels definitely post on GPU modes hackathon challenges um they're very very helpful and very useful um but you know someone managed to hack reward hack the GPU mode kernel competition um and remember in the Matrix multiplication example. There are two there are two there are two checks that we need to do right make the matrix multiplication algorithm faster but also it needs to be correct right there are two checks the correctness check and the timing check. Um and GPU mode also had two checks the correctness check and the timing check. Um and so what do you think the model did when the model the model knew the model actually knew that it was being evaluated on the correctness check right it learned oh I'm being evaluated on the correctness check I will now make correctness correct right so it will output the correct kernel and then the model knew that it was getting timed and what it what did it do it just it just did the algorithm once and then saved it and it skipped all the another 15 um you know tests.

Speaker A: Um and so that's what the model did. So essentially the model learned the model learned that there were two tests, the correctness check and the timing check. And the model only did the correctness check correctly and then once it went into the regime of timing, it cheated. Um to be honest, it's actually quite scary. So essentially the model learned that you're doing these tests and the model actually knows you're doing the benchmarks. Um and so this is actually very interesting. Um and you know, oh yeah, this is this is more an you know, larger example. The correctness check was fine, but the timing check it cheated. Um and all it did is it launch, you know, there was supposed to be 15 calls in the first call. In the first core, it did all 15 of the entire process, right? It did all of the 15 runs. Um and then core two to 15, it just did a Python dictionary look up. Um, yeah.

Speaker B: >> I don't know if you know about this. Reminds me of Volkswagen where they initi.

Speaker A: >> Yes, I someone did tell

Speaker B: >> someone told me about it. Um,

Speaker B: >> this is very similar. It's like, oh, I'm not doing this. Turn this off and

Speaker A: >> Yeah, exactly. So, like, you know, it's not just models, I guess, that cheat. Even humans cheat, I guess. Yes. But I think it's called Goodart's law. That's the one. Like, if you have a benchmark, then the benchmark becomes Is it good law? I don't remember. Yes. Okay. Yeah. The benchmark essentially becomes useless because people just cheat to maximize reward. Um yes, I guess humans also cheat. Um yeah.

Speaker A: Okay. Oh, my favorite example is um so on other labs, you know, you see on Twitter, on wherever, they say they made kernels 10 times faster. Um no, no, no, that's not correct. They did not make kernels 10 times faster. In fact, if you look through the code, they have no, you know, no ops, so no operations. They also edit the timer. You know, they, as I literally described, you know, I described, they, you know, over here, um, you know, they edit the timer, they made matrices go to zero, they cheated. Um, and so like, you know, this actually happened in real world. So some, you know, some of the labs, they published papers claiming that they made kernels 10 times faster. But actually if you read through the code and the examples they these examples all cheated. Um and so you know they you know this is not very good in terms of you know reward hacking. You know reward hacking is a very big problem. Um and you know for example what some of the examples of kernel reward hacking you know not generating real CUDA code instead it cause or some sort of like you know already written system. um you have no up kernels which is essentially making the you know making the A and B matrix just zero. All it does is just doesn't do anything, right? It just the kernel is empty. Um, and you have like memory reuse, so you reuse the same answer over and over again. Um, you have timing synchronization issues. So that's cheating on the timer. Um and my view is like you know if you do publish faster kernels or faster you know matrix if you think that your AI agent has made kernels 10 times faster please verify you know please look through the code before publishing because it is a very it's not a very good look um and so and also the biggest issue that I feel like people are getting forgetting is you know you made kernels 10 times faster you made matrix multiplication 10 times faster There is a

Speaker A: theoretical limit for matrix multiplication, right? Matrix multiplication, you know, it's not you can't make a faster because there's mathematical limits on how to make a faster, right? And so like, you know, matrix multiplication at the very very very olden times, you know, it's O of N cubed. You know, every single time researchers have make it faster and faster and faster and faster and faster. You know, it's now O of N to the^ of 2.371339, I guess. you know researchers every single year are trying to like make this number smaller and smaller and smaller and smaller. Um you know I guess like you know 1 1552 to 1339 is not that small you know not that big I guess. Um but you know they're having progress but the main point is you know these researchers you know they show with mathematical limits you cannot go faster than this and so how can you do reward hacking that is even faster than that. Um and so like the fundamental point is please verify you know to like the people who do research papers and stuff like that please confirm your model is not reward hacking. It is a very big big big problem. Um and you can see oh I think I only had one plot. Um but yes in general please do not do please check your I guess models. Um I guess that's all for the talk. Um you know yeah thank you everyone for coming. Oh more questions as well. Um okay thank you.

Speaker B: Thank you. We also have

Speaker A: Oh, yes. We have a whole bunch of stickers that you can take in the box over there and some pins and stuff.