Today OpenAI is releasing GPT-5.5 and GPT-5.5 Pro into Codex and ChatGPT. Not available in the API quite yet. This model has a higher capacity for complex work and is more efficient, including being more token efficient getting that work done. The whole idea with this model is it's smarter and it's more efficient. So you're going to get more done. GPT-5.5 is $5 per million input tokens and $30 for output tokens. And GPT-5.5 Pro is 30 for a million input tokens and $180 for output tokens. This is a pricey one, but when I reflect on what I was able to achieve with this model in early testing, I'm going to pay the intelligence tax because I think what I was able to achieve is really important. Everything has an ROI and there can be an ROI in terms of speed. But where GPT-5.5 really helps me is ambition. It has been able to do things that literally I have not been able to do before for a couple reasons. One, just intelligence higher. The second thing I've experienced is because the efficiency is higher, I'm able to do more faster without losing context of what I'm working on because it's happening really quickly or it's being more autonomous so I don't have to babysit as much.

We used OpenAI's Codex security product to run a threat assessment and security scan on the codebase. It did come up with some low priority or low severity issues that we needed to remediate. Instead of taking those one by one, what I did is I downloaded the CSV of those issues, upload it to Codex and just said, can you please architecturally review these issues, group them if they're thematic, and then propose a change and then make those changes. It did it very well. We did human review on that. We did code review on that. And we were just really happy with the quality of execution. The real validation of the quality of that output came when we had very quickly after that our annual penetration test and our pen test came back super clean. If you have a list a triage list of technical debt, if you have a triage list of security issues, even maybe front-end debt, flaky tests, engineers, pay attention, you can throw that list at GPT-5.5 and it will get that list done.

We have millions of chats now for ChatPRD and we were storing those chats in various legacy formats as the model providers both OpenAI and Anthropic have changed the shape of their model responses over time. Every model in the world has changed a little bit about how they return data via API. Over the past 3 years, we have a bunch of data debt around that where we were storing legacy formats in our database. These legacy formats because they are AI calls, because they may or may not contain attachments, because they may or may not contain tools, very hard to build a clean cohesive backfill and sanitization of that data into our go forward data model. I have just been slapping fix after fix and patch after patch on this problem because every time we patch it, we find another edge case. I just finally was like you know GPT-5.5 take me away, gave the model that problem and it executed so well, it built functionally one shot a solution that covered 98% of the edge cases. I needed GPT-5.5 and Codex to validate that work. I asked Codex: I need you to make a scalable system for our team to do this programmatically, ideally through a CLI so that any agent can test any thread. I trust you to make a call, figure out how to spawn a sub agent to do this, test it, and identify any issues, repair them, and get this ready for production. This thing worked for 6 hours. It was actually 5 hours and 57 minutes. I did not have to— zero prompts, zero follow-ups, zero steering. It just went for 6 hours. This thing will do long-running autonomous tasks that require a loop to understand if it's doing well and moving things forward. After two million rows we had one edge case that was not caught. We saw our error rate just hit the floor in our monitoring. People say that AI coding is going to decrease quality because people are vi coding. That is just such an 18 months or 12 months ago narrative. I think quality is going to go up. Just being able to hand this to GPT-5.5 and Codex has changed my life.

This is a Doom Mini2 retro PC style Bluetooth speaker and tiny screen. I have been hacking on this thing since January. My only goal is to be able to display funny stuff on this screen. It comes with an out-of-the-box iPhone app, but I don't want that. I live in the terminal. I want to be able to do this programmatically. This is like proprietary code loaded on this device. I was very deep in Chinese language repositories and documentation. I threw Cloud Code at this and said, "Can you figure this out?" Cloud Code could not figure it out even with Opus. I threw GPT-5.4 four at it. It could not figure it out. It connects to your phone via Bluetooth. It is interacting with this app on your phone through Bluetooth and in the app I can like draw something and click send and it will display here. But we could not figure out how to encode that message. I spent truly hours downloading a Bluetooth profiling profile on my phone for developer debugging. I then hooked it up to a packet sniffer so that when I was using the app here on my phone and it sent an image to this device, it would log and sniff the packets and tell me what Bluetooth was sending to this little guy. I threw these logs and all the information that I had at 5.5. I said, "This thing is connected by Bluetooth. Take what you know and please just do anything to figure out how to display on this. You have so much information. You should know how to do it. I believe in you." And guess what? This effing thing did it. It did it. I was able to build a command line tool where I can run it in terminal. Press enter. This is months, months, months of trying to hack into this stupid thing. It was encoding and decoding bitmap files. It was crawling the web trying to find if there was some secret SDK. Codex, you did the thing. And even better than that, it is now hooked up so that anytime I ask Codex to do a thing, it will alert me on this.

It has the baked potato personality that we've all come to know and love from Codex. It is a dull dull character, but I learned over the testing of this, if you do /personality in Codex, you're able to change that to something a little friendlier. And while some of my fellow early testers said it had too much of a Gen Z personality, I said, "I like to stay young. Give me that Gen Z GPT-5.5. I'll take it any day over the paper bag baked potato personality that you get out of the box." For senior software engineers and staff software engineers, I'm going to go blow through a bunch of technical work and I really love this model. Throw this thing at your quality issues. Throw this thing at your bug backlog. Throw this thing at a security assessment and close the quality gaps or performance gaps or security gaps in your app. It does really, really, really well.