---
author: Latent Space
date: '2026-10-31'
guest: ''
layout: post.njk
source: https://www.youtube.com/watch?v=v-d1WTqIULs
speaker: Latent Space
tags:
- financial-services
- enterprise-ai
- model-evaluation
- rlhf
title: OpenAI 金融服务负责人 Joseph Kim 访谈：打造 ChatGPT 金融产品与模型品味训练
summary: OpenAI 金融服务负责人 Joseph Kim 探讨了 ChatGPT for Financial Services 的构建逻辑、捆绑企业数据的原因、基于插件架构的开发，以及通过人类偏好与强化学习训练模型审美与判断力的未来路径。
insight: ''
draft: true
series: ''
category: ai-application
area: tech-engineering
project: []
people:
- Joseph Kim
companies_orgs:
- OpenAI
- Morgan Stanley
- Evercore
products_models:
- ChatGPT
- Codex
- GPT-6 Astra
media_books: []
status: evergreen
---
>> 我真的认为，基于 ChatGPT 插件将会诞生价值十亿美元的业务。但我们所构建的内容中，有 95% 是初创公司或其他公司完全也能做出来的。
Original English
>> I
I
really
do
think
that
there's
going
to
be
a
billion
dollar
business
built
on
top
of
a
chat
GPT
plugin.
But
95%
of
what
we
built
was
something
that
absolutely
a
startup
could
do,
another
company
could
do.
Original English
>> At
OpenAI,
we
ran
into
problems
with
pre-training
and
therefore
had
difficulty
scaling
the
model.
In
2026,
we've
been
able
to
solve
many
of
these
issues.
Original English
>> [music]
Original English
>> Today
we
have
Joseph
Kim,
one
of
the
heads
of
chat
GPT
finance
from
OpenAI,
and
our
co-host
and
head
of
editorial
from
Latent
Space,
Richard,
in
the
studio.
It's
a
special
episode.
We're
here
in
New
York
at
AI
Finance.
Joseph
just
gave
a
great
keynote.
I
think
we
don't
want
to
repeat
most
of
the
information,
so
honestly
go
watch
it,
but
give
give
like
a
30-second
of
what
you
talk
about
and
then
we'll
leave
the
breadcrumbs.
You
guys
can
go
watch
the
keynote.
Original English
>> Sure,
yeah,
I
can
give
a
quick
30-second
intro
to
kind
of
what
we
just
chatted
about.
One,
I
would
say
like
we
just
released
a
new
product,
chat
GPT
for
financial
services.
This
is
an
enterprise-focused
product
that's
really
trying
to
bring
the
power
mix
the
power
of
chat
GPT,
kind
of
the
tools
and
things
that
you
really,
you
know,
like
to
use
in
the
consumer
product,
but
also
add
in
the
enterprise
layer
so
that
firm-specific
templates,
you
know,
sources
like
Dilupa,
S&P,
etc.
And
so
really
exciting.
We've
been
working
with
our
design
partners
Morgan
Stanley
and
Evercore
on
that,
and
reception
to
that's
been
incredible.
So
that
was
kind
of
the
first
half
of
the
talk.
And
in
the
second
half
of
the
talk,
really
much
more
forward-looking,
so
thinking
deeply
about
some
of
the
trendlines
that
we're
seeing
in
terms
of
model
improvements,
and
drawing
those
trendlines
out
to
the
future
and
trying
to
think
a
little
about,
okay,
like
what
are
these
models
going
to
be
able
to
do
at
the
end
of,
you
know,
mid-2027,
end
of
2027,
and
what
does
that
mean
for
folks
that
are
building
products
on
top
of
that
model,
and
how
can
you
kind
of
start
to
plan
ahead
to
the
intelligence
that
comes
in,
you
know,
just
a
matter
of
months.
Original English
>> I think
it's
a
fun
time
because
you
actually
come
from
the
research
side
of
things.
So
you
now
lead
a
lot
of
the
product
and
engineering,
but
tell
us
what
it
takes
to
make
a
financial-specific
product.
You
mentioned
in
the
keynote
that
there
was
sort
of
an
uptick
in
users
when
you
launched
ChatGPT
work.
So,
Codex
started
to
become
available
to
the
masses.
People
start
using
it
for
finance,
and
now
you're
shipping
your
first
finance
product.
What
is
like
financial
reasoning
data
like?
What
goes
into
finance
specific
models?
Original English
>> Yeah,
it's
it's
a
great
question.
I
mean,
one
thing
I
will
say
is
that
like,
you
know,
all
of
the
training
data
that
we
do
for
financial,
you
know,
reasoning
analysis,
we
do
upstream
into
what
we
call
the
big
run,
which
is
the
the
main
kind
of
run
that
becomes,
you
know,
something
like
6
Astra
or
61
Astra,
etc.
And
so,
even
though
we're
adding
a
bunch
of
financial
data
to
the
model,
it's
going
into
the
main
main
model,
and
so
therefore
it's
available
to
folks
that
want
to
build
on
top
of
it.
And
that
is
something
that's
very
important
to
us.
You
know,
at
OpenAI,
we
really
do
want
that
intelligence
to
be
accessible
not
only
to
our
products
that
we're
building
in-house
in
first-party
ways,
but
also
for
folks
that
want
to
build
startups,
build
businesses
on
top
of
that,
as
well
as,
you
know,
financial
firms
that
want
to
integrate
that
directly
into
their
companies.
And
so,
we
will
make
all
that
intelligence
accessible
there.
I
think
you
touched
a
little
bit
on
product
and
research,
and
I
think
that's
like
really
core
to
what
we
do
at
OpenAI.
Internally,
we
call
ourselves
a
research
and
deployment
company.
And
so,
what
that
means
and
we
kind
of
structure
that
in
order
on
purpose,
like
research
comes
first,
and
then
deployment
comes
second.
And
so,
as
we
think
about,
you
know,
at
the
end
of
the
day
trying
to
change
the
way
that
people
do
knowledge
work,
we
kind
of
work
in
that
order,
right?
We
think
about
the
model
capabilities,
where
they're
headed,
what
kind
of
new
things
they
enable.
So,
that's
one.
And
then
two,
we
think
very
deeply
about
the
product
features
and
surface
areas
that
we
should
build
to
make
that
model
intelligence
accessible
to
more
people.
And
I
think
you
alluded
to
to
a
slide
in
my
my
um
keynote
where,
you
know,
we
had
this
chart
of
Codex
adoption
within
OpenAI.
And
it's
funny
because
you
can
you
can
see
the
the
software
engineering
adoption
curve,
and
it's
just
like
up
into
the
right
pretty
steady.
People
are
picking
it
up
and
and
incorporating
into
their
daily
routines.
But
if
you
look
at
finance
finance,
legal,
and
sales,
you
know,
it's
pretty
much
at
zero,
and
suddenly
it
kind
of
jumps
up
to
90%
and
if
you
and
if
you
look
at
that
line
and
try
to
see
what
happened
around
the
time
where
it
jumped
up,
we
we
had
released
Codex
desktop
app,
um,
you
know,
in
February
and
that
was
when
that
adoption
jumped
up.
And
so,
I
do
think
it
kind
of
shows
the
importance
of
co-developing
those
things
and
the
purpose
of
the
product
is
to
make
that
model
intelligence
accessible
to
as
many
users
as
possible.
Original English
>> So,
in
the,
you
know,
that
uptick
of
data
for
using
Codex
for
financial,
you
know,
applications,
what
sort
of
things
did
you
learn
that
you
then
applied
into
the
post-training
of
financial
data?
Original English
>> Yeah,
it's
a
good
question.
I
would
say
like,
yeah,
I
could
talk
a
little
bit
about
how
we
went
about
building
ChatGPT
for
financial
services.
It's
it
was
very
unique.
We
we
haven't
built
a
whole
lot
of
first-party
products.
I
would
say
like
Codex
was
really
like
our
biggest
and
main
one
and
it
was
the
first
time
we
developed
a
product
where
the
product,
the
model
hardness
and
the
the
research
was
all
kind
of
under
one
house
and
under
one
roof
and
it
really
gives
us
a
lot
of
flexibility
to
go
about
building
things.
I
think
the
biggest
takeaway
that
I
have
from
having
worked
on
this
for
the
last
6
months
or
so
is
in
enterprise,
it's,
you
know,
you
have
to
deal
with
the
reality
of
the
industry
that
you're
in
and
go
build
around
that.
And
I
think
that
piece
is
it's
easy
to
ignore.
Like
if
you
just
think
about
it
from
first
principles,
you
can
come
to
a
conclusion
that
makes
sense
and
you
talk
about
it
and
you
can
defend
it
with,
you
know,
with
logic
and
reason.
But
if
you
ignore
the
state
of
the
world
that
you
're
in
when
you
start
building
and
the
forces
that
are
at
play
within
the
industry
to
try,
you
know,
it's
either
competitive
forces,
people
have
their
own
objectives.
And
if
you
just
don't
think
about
that,
you're
not
going
to
build
the
right
product,
right?
And
so,
we
saw
that
with,
um,
ChatGPT
for
financial
services.
We
thought
about
that
a
lot.
I'll
give
you
one
example.
Um,
data.
Data
is
like
a
huge
part
of
how
we
thought
about,
um,
building
the
product.
And,
you
know,
and
and
data
was
one
of
those
things
where
on
first
principles
it
was
a
little
bit
tough
when
I
was
talking
about
build
working
on
this
product
to
defend
because,
you
know,
you
say,
"Hey,
like
I
want
to
go
and
bring
quarter
earnings
transcripts
into
the
product
and
bundle
it."
And
the
first
question
that
the
first
thing
people
are
going
to
say
are
is,
"Look,
there's
an
MCP
connection
in
the
store.
Like
what
is
what
is
the
incremental
value
that
you're
providing
by
at
bundling
that
in?
On
paper
it
looks
bad.
It's
like
you
can
they
might
already
have
a
license
for
it,
so
they
might
feel
like
they're
paying
twice
for
it.
Um
and
they
might
have
an
MCP.
And
so
like
why
are
you
building
this?
And
the
reality
is
we
went
and
we
tested
all
these
MCPs.
And
what
we
found
was
the
error
rates
were
were
really
really
high.
Some
some
of
the
MCPs
that
we
connected
some
big
names
40%
plus
error
rate
on
their
MCPs,
right?
And
so
um
MCPs
is
one
of
those
things
where
it
it
looks
way
on
paper,
but
you
have
to
go
see
look
at
the
data
and
see
what's
actually
going
on.
And
so
for
data
we're
like,
"Hey
look,
this
is
really
bad.
The
only
way
we
can
go
about
fixing
this
at
scale
is
to
bring
the
data
in
house,
like
just
control
that
experience
end
to
end."
And
the
extra
money
that
you
pay
on
top
to
bundle
that
data
is
worth
it,
right?
And
so
that
was
a
product
decision
that
we
had
to
make
that
was
very
industry
specific.
Um
and
it's
been
resonating
with
customers.
Customers
love
it.
They
you
know,
the
number
one
thing
they
call
out
is
the
data.
And
so
um
it
worked.
Original English
>> So,
you
had
good
success
in
this.
Tell
us
about
the
technical
side
of
things
for
people
building
a
harness
adaptation
for
a
specific
service,
right?
So,
you
guys
went
out,
you
changed
Codex,
you
did
post
training,
you
did
whatever
you
did
to
make
ChatGPT
for
financial
services.
If
someone
was
to
do
the
to
do
the
same
for
another
domain,
say
legal,
sales,
whatever,
uh
what
are
the
best
practices
there?
What
did
you
learn?
What
goes
into
just
taking
off
the
shelf
and
actually,
you
know,
making
a
certain
product
around
it?
Original English
>> Yeah,
it's
a
yeah,
I
like
the
question
a
lot.
Um
it
it
you
know,
I
tried
to
allude
to
this
in
my
keynote
as
well,
but
the
like
interesting
thing
is,
you
know,
it's
fun
to
talk
about
the
post
training
stuff
because
it's
unique
to
what
we
do
and
uh
gets
people
excited,
but
95%
of
what
we
built
was
something
that
absolutely
a
startup
could
do,
uh
another
company
could
do.
And
we
didn't
really
have
to
go
leverage
our
ability
to
go
make
changes
in
the
model
to
go
about
building
fantastic
product,
right?
And
so
I
think
it's
a
great
call
to
kind
of
mention
that
piece.
Um
what
I
would
say
is
like
uh
twofold.
One
is
most
of
the
product
that
we
built
was
built
on
top
of
the
Codex
um
or
I
should
say
ChatGPT
now,
um,
plugin
architecture
and
plug
and
primitives.
And
that
is
something
that
we've
been
investing
a
lot
of
time
and
energy
in.
Um,
you
know,
OpenAI
is
like
an
interesting
company
where,
you
know,
we
have
we
kind
of
face
the
same
problems
internally
that
a
startup
would
face,
uh,
if
they
were
to
build
on
top
of
OpenAI.
So,
in
very
in
a
lot
of
ways
like
my
team
is
kind
of
like
a
startup
that's
building
on
top
of
OpenAI
technology,
right?
And
so,
um,
even
internally,
we
need
to
find
scalable
ways
for
teams
like
myself
to
stand
on
the
shoulders
of
giants
and
build
on
top
of
Codex,
right?
The
Codex
is
fantastic.
Um,
it's
got
great
memory.
It's
got
good
skills.
Like
there's
a
you
know,
it's
persistent.
Um,
there's
a
lot
of
things
that
are
wonderful
about
Codex,
but
the
thesis
of
my
team
was
Codex
was
Codex
will
get
you
about
80%
of
the
way
to
a
product
that
would
be
successful
in
the
market,
but,
you
know,
um,
the
20%
is
missing.
And
so,
we
need
to
find
some
way
for
my
team
to
go
build
that
20%
to
actually
go
win
cuz
the
other
half
of
the
thesis
was
if
you
just
took
Codex
and
launched
it
as
a
finance
product,
um,
it
would
fail.
And
so,
that
20%
is
actually
pivotal.
And
so,
what
I
would
say
is
we
we
went
and
we
built
on
top
of
the
plugin
architecture.
It's
using
the
same
primitives
that
are
available
to
any
of
the
builders
that
want
to
go
build
on
top
of,
um,
ChatGPT.
And
I
you
know,
I
had
a
line
in
my,
um,
presentation,
but
I
I
really
do
think
that
there's
going
to
be
a
billion-dollar
business
built
on
top
of
a
uh
ChatGPT
plugin,
right?
Like
it's
like
you're
going
to
be
able
to
leverage
all
of
that
horizontal
functionality
and
just
add
your
secret
sauce
on
top.
And
that
secret
sauce
might
be
data,
it
might
be
UI
changes,
um,
it
could
be
an
integration,
but,
you
know,
that
secret
sauce
is
really
valuable
and
I
think
there's
there's
a
billion
dollars
worth
of
value
to
be
built
there.
Original English
>> So,
uh,
yes,
it's
an
interesting
time
for
the
industry
cuz
we're
at
a
a
time
now
where
orchestration
is
uh
is
becoming
a
lot
more
automated,
you
know,
teams
of
agents
going
out
and
doing
things.
But
for
finance,
obviously,
there
are
a
lot
of
risks
uh
involved
in
that.
So,
can
you
talk
a
bit
about
about
the
safety
sort
of
uh
that
you've
baked
into
the
product?
Original English
>> Yeah,
um,
safety
is
super,
super
important.
Um,
I
would
say
that
like
and
it's
only
going
to
get
more
important
uh
because
the
you
know,
the
agents
are
already
getting
more
autonomous
and
more
independent.
And
I
think
that
trend
we
expect
it
to
continue
into
'27
and
into
'28.
Um
I
would
say
if
uh
for
the
for
the
product
that
we
built
and
launched
last
month,
um
we
there
was
a
bunch
of
paradigms
that
already
existed
um
as
it
pertains
to
safety
um
and
you
know,
being
thoughtful
around
auditing
the
work,
making
sure
that
the
model's
not
making
a
mistake
that's
going
to
impact
business
outcomes.
And
we
were
able
to
lean
heavily
into
those.
And
and
what
I
would
say
is
the
existing
product
that
we
launched
is
a
productivity
tool
for
knowledge
workers
working
in
this
space.
And
so
the
idea
behind
it
is
there's
a
a
deep
assumption
that
there's
always
a
human
in
the
loop,
right?
Like
So
the
idea
there
is,
you
know,
you're
a
financial
analyst
and
you
have
a
a
laundry
list
of
things
you
want
to
get
done
that
day.
And
and
just
like
how
a
software
engineer
would
do
with
Codex,
for
every
one
of
those
items,
the
first
thing
you
do
is
try
to
build
it
with
ChatGPT,
right?
And
it
might
get
you
30%
of
the
way
there,
it
might
get
you
80%
of
the
way
there
depending
on
the
task,
but
there's
always
this
presumption
of
humans
in
the
loop
uh
that
are
presiding
with
that
work.
And
um
that
made
it
very
easy
for
us
to
to
build
a
product
where
we
could
kind
of
pass
off
the
responsibility
of
auditing
review
uh
into
the
people's
hands
and
into
people's
responsibilities.
And
that
worked
for
us
well
and
it
was
easy
to
communicate.
Um
so
that
was
wonderful.
I
will
say
we're
thinking
very
deeply
about
what
comes
next.
And
and
what
comes
next
looks
different
uh
than
than
a
productivity
tool
um
that
sits
and
and
is
always
being
monitored
by
a
human.
And
I
think
as
we
think
about
what
comes
next,
there's
kind
of
two
things
we're
thinking
about.
One
is
how
do
we
kind
of
shape
the
security
safety
profile
of
the
product
into
something
that
people
understand
intuitively.
And
some
I
would
say
something
that
people
understand
very
intuitively
is
how
to
work
with
other
people.
Um
and
so
our
thesis
is
if
we
make
the
product
very
similar
to
how
you
work
with
your
your
co-workers,
your
interns,
people
around
you,
that
is
something
that
people
can
pick
up
and
learn
very
quickly,
very
easily.
And
we
And
therefore
we
need
to
shape
the
security
profile
of
that
to
look
like
a
person.
And
so
there's
a
few
things
I'll
call
out
there.
One
is
there's
this
notion
of
read-write,
uh
uh
you
know,
even
for
people.
Like,
uh
you're
a
new
software
engineer
at
a
company,
you
oftentimes,
you
know,
I
was
at
Google,
you
need
you
need
something
called
readability.
And
so,
there's
these
kind
of
like
checks
and
balances
and
systems
in
place
before
you
can
start
mucking
around
touching
the
system.
And
so,
there's
already
systems
in
place
to
monitor
the
work
of
people.
So,
if
if
models
behave
more
like
people,
then
you
can
leverage
those
systems.
And
that
makes
it
very
easy
to
kind
of
talk
about
and
work
through
this
um
with
these
financial
institutions.
So,
that's
something
we're
leading
into
pretty
heavily
coming
up.
And
the
very
last
thing
I
would
say
is,
at
least
in
the
context
of
banking,
which
is
where
we
kind
of
started,
um
there's
already
this
system
in
place
for
junior
analysts
doing
a
lot
of
the
groundwork.
Uh
their
work
gets
passed
off
to
associates.
Associates
are
reviewing
the
work.
Um
then
the
associates
are
kind
of
adding
their
secret
sauce,
their
magic,
their
reasoning.
That
gets
passed
off
to
the
VP.
VP
goes
up
to
the
director,
managing
director.
So,
there's
this
kind
of
like
a
hierarchical
system
where
there's
this
implicit
work
checking
that's
happening.
That's
already
been
built
out
to
stop
uh
to
try
to
prevent
against
uh
mistakes
that
humans
make,
right?
Like
humans
make
just
as
many
mistakes
as
models.
And
so,
there's
systems
that
are
built
there.
And
so,
we're
also
leaning
heavily
in
terms
of
those
systems
as
it
as
it
pertains
to
building
financial
products.
Original English
>> Okay.
Original English
>> I
say
there's
this
like
sort
of
misconception
where
in
the
finance
world,
one
mistake
really
compounds.
Like
your
your
whole
career
is
at
risk
if
you
submit
something
wrong.
How
should
people
think
about
getting
started
in
using
it?
So,
if
you're
an
analyst,
um
how
should
you
use
these
tools?
And
do
you
have
like
any
analogies
towards
where
we're
at
right
now?
So,
there's
like
levels
of
self-autonomy
in
self-driving.
One
of
your
slides
I
think
said
like
2027
you
see
no
more
PowerPoint.
A
lot
of
people
will
be
using
AI
tools
in
the
loop.
Original English
>> Yes.
Original English
>> So,
how
should
people
think
about
where
we
are
now
and
where
things
are
going
and
how
should
they
adopt
these
tools
if
they
have
that
misconception
of
like
one
mistake,
my
career's
over.
Original English
>> Yes.
Original English
>> Obviously,
there's
human
in
the
loop,
but
how
should
they
also
think
about
it
going
forward
as
they
need
to
offload
more
and
more
or
Original English
>> Yeah.
No,
that's
that's
wonderful.
Um
I
I
have
two
perspectives
on
this.
And
they
come
they
start
with
different
assumptions.
Um
I
think
I
I
think
the
notion
that
like
my
career's
over
if
you
make
one
mistake
is
an
incorrect
notion.
And
I
have
a
line
of
thought
that
like
follows
that.
But
let
me
let's
the
first
assume
that
it's
true,
right?
And
and
in
the
case
that
it's
true,
what
I
would
say
is
like
not
all
mistakes
are
created
equally
and
not
all
model
capabilities
are
created
equally.
And
so
when
you
think
about
the
mistake
that
a
model
or
a
human
could
make
that
could
be
career
ending,
you
know,
it's
it's
usually
once
you
get
up
to
a
certain
level.
Like
if
you're
a
you
know,
VP
the
stakes
are
higher
than
when
you're
a
junior
analyst
because
there
is
a
presumption
of
work
having
been
checked
up
to
that
point.
So
if
an
MD
MD
sees
a
mistake,
that's
a
huge
problem.
A
lot
of
the
safety
nets
have
been,
you
know,
have
failed
for
that
mistake
to
make
it
up
to
an
MD,
right?
Um
but
what
I
would
say
is
like,
you
know,
the
career
ending
mistake
is
something
where
you
get
a
piece
of
information
factually
incorrect.
And
that
piece
of
factual
information
changes
the
conclusion.
Like
that
is
obviously
like
the
kind
of
the
biggest
type
of
mistake
that
you
can
make.
And
what
I
would
say
is
we're
seeing
a
lot
of
progress
in
in
attention
to
detail.
And
you
know,
the
hallucination
used
to
be
a
big
term
that
used
to
come
up
in
2022,
2023
that
doesn't
come
up
nearly
as
often
nowadays.
I
would
say
that
like
we're
starting
to
see
huge
improvements
in
the
liability
of
models
as
it
pertains
to
factual
mistakes.
So
the
the
kind
of
egregious
mistake
that
would
get
you
fired,
models
are
getting
much
better
at
and
continue
to
get
much
better.
And
so
I
feel
actually
quite
confident
that
a
combination
of
that
continual
improvement
plus
the
existing
system
checks
in
place
are
will
make
it
such
that,
you
know,
that
type
of
mistake,
the
chance
of
that
propagating
up
to
an
MD
is
just
very
low
probability,
right?
What
I
would
say
the
models
are
lacking
today
and
they
still
need
to
improve
is
actually
not
the
career
ending
mistake,
but
it's
the
it's
the
bit
that
involves
human
judgment
and
taste.
So
it's
the
this
slide
looks
ugly,
right?
And
it's
it's
not
wrong,
but
it's
formatted
like
the
colors
look
a
little
bit
off.
Something
about
it
looks
sloppy
and
therefore,
you
know,
this
is
not
a
good
slide.
And
and
that's
that's
not
a
career
ending
mistake
in
the
way
that
in
in
like
a
factual
mistake
is,
but
it
It
matters.
It
still
matters
in
terms
of
how
useful
that
work
is.
And
so,
as
we
think
about
the
progression
in
going
into
2027,
what
I
would
say
is
I
expect
the
model
to
get
much
better
at
the
human
taste
component.
And
that's
what
I
was
kind
of
alluding
to
in
my
keynote
is
I
think
the
model
will
get
much
better
at
human
taste
on
things
that
are
softer
objective
functions.
It's
not
is
it
right
or
wrong?
It's
comparative.
It
Is
there
something
that's
better
than
this?
And
I
think
models
are
going
to
get
much
better
along
that
dimension
moving
forward.
Original English
>> How
so?
How
do
we
solve
taste?
How
do
we
train
taste
into
the
models?
Um
Original English
>> Yeah.
I
So,
it's
funny.
Like
very
early
on
in
the
like
early
early
chess
days,
the
only
thing
we
trained
models
on
were
essentially
taste,
right?
Like
the
there
was
reinforcement
learning
through
human
feedback.
And
the
human
feedback
was
always
a
pairwise
signal.
It
was
like
given
two
options,
which
one's
better?
And
so,
the
early
days
of
reinforcement
learning
were
built
on
the
notion
of
training
on
human
taste.
Uh
and
then
obviously
things
like
verifiable
rewards
and
environments
and
all
you
know,
we
built
a
lot
of
machinery
to
do
other
types
of
rewards
and
other
types
of
RL.
And
so,
people
kind
of
forgot
that
a
lot
the
early
days
of
of
RL
reinforcement
learning
were
all
around
human
taste.
And
so,
how
do
you
train
on
human
taste?
It's
I
think
the
technical
answer
is
quite
simple.
I
think
the
like
practical
answer
obviously
is
more
complicated.
Um
the
practical
answer
is
you
just
train
a
reward
model,
right?
You
just
train
a
reward
model.
You
get
a
bunch
of
humans
to
look
at
pairs
of
things
and
say
which
one
is
better.
And
this
still
works.
Um
so,
like
um
fun
fact,
like
we
did
this
for
our
slides,
right?
Like
I
mean,
how
do
you
how
do
you
go
about
making
these
models
better
at
generating
presentations?
Well,
we
just
get
a
bunch
of
humans
to
look
at
pairs
of
slides
and
say
which
one
looks
better.
And
humans
are
actually
really,
really
good
at
aesthetic
um
judgment,
right?
Actually
much
better
than
models
is
something
that
we
discovered.
Is
like
a
human
can
look
at
two
slides
and
within
seconds
say
this
one
looks
better.
And
if
you
have
a
model,
like
a
grading
grading
model,
try
to
go
about
doing
that,
um
it's
going
to
spend
a
whole
bunch
of
reasoning
tokens
this
pixels
this
way,
this
thing's
that,
uh
and
then
maybe
comes
to
the
wrong
conclusion.
And
so,
humans
are
still
really,
really
valuable
in
making
these
models
better.
And
so,
we
will
we
will
rely
a
lot
on
uh
human
preference
um
to
imbue
things
like
taste.
So,
that's
one.
Um,
the
last
thing
I'll
kind
of
add
is
there's
precedent
for
this,
which
makes
us
confident
that
this
strategy
will
work.
And
that
precedent
I
would
say
is
coding.
Um,
the
models
have
gotten
I
would
say
coding
is
not
fully
solved,
but
like
let's
say
we're
80%
of
the
way
there
and
we're
making
progress
on
the
on
the
last
20%.
Um,
coding
is
a
combination
of
verifiable
rewards
and
human
taste,
right?
And
so,
the
verifiable
rewards
are,
you
know,
does
the
does
the
code
compile?
Are
there
syntax
errors?
Um,
is
the
output
of
the
function
expected?
Um,
and
so
there's
these
verifiable
power
rewards
that
are
in
place,
but
a
lot
of
good
software
engineering
is
um,
is
this
clean
system
design?
Did
you
build
a
system
that's
maintainable
over
time?
Um,
is
it
easy
to
unit
test?
Is
it
following
paradigms
that
the
vast
majority
of
the
community
or
the
um,
industry
thinks
is
the
right
paradigm?
And
if
you
look
at
it
from
that
lens,
um,
financial
uh,
a
lot
of
financial
work
looks
very
similar.
It's
the,
you
know,
I
have
an
Excel
model,
does
it
sum
up?
Are
there
reference
errors?
There's
a
whole
bunch
of
verifiable
things
that
we
can
check
to
make
sure
that
the
work
is
passing
this
the,
you
know,
first
pass
sanity
check,
but
there's
also
a
lot
of
is
this
the
way
I
would
have
built
this
model?
Um,
something
I
learned
about
as
I
started
working
in
finance
is
there's
this
notion
of
like
the
feel
of
the
model,
which
is,
you
know,
you
you
kind
of
perturb
the
inputs
and
you
look
at
the
outputs.
And
an
experienced
financial
professional
can
kind
of
perturb
the
inputs,
look
at
the
outputs
and
kind
of
understand
does
the
data
flow
through
this
model
in
a
way
that
feels
good,
right?
And
that
is
a
human
preference
that
looks
a
lot
like
does
this
code
look
clean?
Is
it
well
written?
And
I
think
our
success
in
coding
gives
me
confidence
that
we
can
solve
a
lot
of
these
problems
in
finance
as
well.
Original English
>> Yeah,
we
can
shout
out
a
frontier
code
from
cognition.
So,
it's
not
only
like
sweet
bench
is
very
um,
you
know,
is
the
answer
correct?
This
is
also
would
you
merge
the
code?
So,
you
can
have
multiple
answers
that
are
proper
PRs
that
pass,
but
which
one
would
you
merge?
And
that's
why
you
sometimes
see
the
charts
of
lower
reasoning
is
better,
but
it's
a
taste
benchmark
as
well,
right?
Original English
>> Yeah.
And
uh,
one
of
your
other
2027
predictions
I
thought
was
interesting
was
that
uh,
you
know,
the
models
that
you're
training
will
become
much
better
at,
you
know,
investment
thesis
and
sort
sort
generating
ideas
for
investment
and
trading.
Um
but
obviously,
you
know,
uh
that's
something
that
humans
are
uh
well
experienced
kind
of
financial
professionals
are
very
good
at
and
they
kind
of
have
an
intuition
for
that
kind
of
thing,
but
it's
often
counter
to
the
prevailing
wisdom
out
there.
Otherwise,
you
know,
uh
there's
less
of
a
chance
of
it
making
a
a
great
return.
So,
how
how
are
you
tackling
that
problem
in
terms
of
training
the
agents
to
do
that
kind
of
work?
Original English
>> Yeah.
Um
I
would
say
that
like
up
until
date,
the
vast
majority
of
applications
of
AI
in
finance
have
been
really
focused
on
I
would
say
like
the
junior
analyst's
work.
Um
and
I
think
that's
I
think
that's
for
two
reasons.
One
is
you
have
to
build
the
product
based
on
the
like
capabilities
of
the
model
of
today.
And
so,
if
you
look
at
the
capabilities
of
the
model
today,
they're
really
quite
good
at
taking
pretty
concrete
instructions
of
what
to
do
and
kind
of
executing,
right?
So,
build
me
a
slide,
I
want
it
to
look
this
way,
you
know,
make
it
look
good,
use
our
template,
these
types
of
things.
The
model's
quite
capable
of
doing
those
things
and
so
therefore,
we've
built
product
experiences
around
that.
Um
and
the
other
thing
I'll
call
out
is
um
there
is
a
strong
preference
to
make
the
model
good
at
things
that
humans
are
not
good
at
or
don't
like
to
do,
right?
And
so,
uh
human
you
know,
most
humans
I
talked
to
there's
obviously
exceptions,
but
a
lot
of
the
humans
I
talked
to
like
um
humans
I
talked
to
people
I
talked
to.
Um
[laughter]
uh
you
know,
they
really
don't
like
building
Excel
models.
It's
a
tedious
kind
of
work
and
it's
very
detail
oriented,
it's
easy
to
get
wrong.
And
similarly
with
slides.
Um
you
know,
you're
you're
copying
logos,
you're
placing
them
very
precisely
on
a
specific
part
of
the
page.
That's
very
tedious
work
that
a
lot
of
people
don't
like
to
do.
And
so,
that's
been
part
of
the
impetus
for
us
to
go
and
focus
on
some
of
these
tasks,
right?
It's
a
combination
of
two
of
those
things.
There's
the
like
existing
model
capability
is
pretty
good
at
uh
certain
types
of
task
and
also
human
preferences
of
what
they
like
to
do
and
not
like
to
do
helps
drive
the
direction
of
the
product
as
well,
right?
It's
a
combination
of
those
two
things.
Um
I
think
that
like
we've
solved
a
lot
of
the
low-hanging
fruit
of
those
two
things.
And
so,
going
into
2027,
we're
going
to
start
to
move
up
the
stack,
right?
We're
going
to
go
from
the
task
that
a
junior
analyst
can
do
to
some
of
the
tasks
that
an
associate
can
do
to
some
of
the
tasks
that
an
MD
would
do
and
move
up
that
chain.
And
as
you
move
up
the
chain,
what
I
would
say
is
the
objectives
become
much
fuzzier.
It
goes
from
this
is
clearly
a
good
or
bad
slide,
or
something
that
we'd
put
in
front
of
a
client
or
not,
to
well,
I
don't
know
if
this
investment
idea
is
good.
And
it's
And
it
would
take
me,
you
know,
3
years
of
waiting
to
really
be
able
to
give
you
a
a
clear
concrete
answer
of
like
what
the
market
has
done.
And
so
the
objectives
start
to
become
fuzzier.
And
so
the
the
way
you
go
about
training
the
model,
and
the
way
you
think
about
how
to
make
the
model
better,
those
things
becomes
more
difficult.
It
becomes
more
difficult
from
a
research
perspective.
And
so
um
but
it's
not
impossible,
is
what
I
would
say.
And
so
what
it
takes
is
a
lot
of
research
focus.
It
takes
a
lot
of
wonderful
data.
It
takes
a
lot
of
feedback
from
experts
in
the
field.
We
really
want
to
get
the
the,
you
know,
the
P99.9
type
of
feedback
uh
to
make
the
model,
you
know,
as
good
as
humans.
But
I
don't
think
it's
an
insurmountable
problem.
And
I
And
And
what
it
takes
is
continued
scaling
of
the
base
model,
and
focus.
Focus
from
the
research
labs
who
think
that
this
is
an
important
problem
to
go
solve.
And
one
of
the
things
that
I'm
doing
at
uh
on
my
team
is
making
this
a
area
of focus
and
priority
for
OpenAI.
And
And
I
think
because
of
the
combination
of
those
two
things,
I
feel
confident
we'll
make
a
lot
of
strides
in
2027.
Original English
>> Do
you
have
any
comments
on
any
of
the
current
financial
benchmarks?
So,
I
think
we're
still
in
the
state
of,
you
know,
uh
does
this
check
out
numbers-wise?
Uh
how
do
you
think
about
making
your
own,
adding
in
taste?
Um
I
think
this
is
also
an
open
call
for
people
working
in
this
space
to
work
on
their
own
benchmarks.
And
a
sort
of
follow
along
to
that
is,
you
said
build
for
build
systems
for
models
today,
but
you
also
give
a
lot
of
predictions
for
the
future.
Um
how
do
you
put
guardrails,
limitations,
um
checks
on
financial
services
that
you
build
for
people
today,
just
so
they're
confident
in,
you
know,
this
is
not
like
going
out
off
the
rails?
Original English
>> Yeah,
makes
sense.
Um
let's
Yeah,
let's
talk
a
little
bit
about
evals.
Uh
evals
is,
yeah,
something
near
and
dear
to
my
heart.
I
spend
a
lot
of
time
working
on
evals.
I
would
say
that
um
the
like
um
the
prior
that
I
would
share
with
people
is
building
a
good
eval
is
incredibly
hard.
Peop-
Pe-
you
know,
that's
not
obvious
to
people
who
haven't
worked
on
an
eval
before.
Um
to
build
an
eval
that
actually
like
correlates
with
the
thing
that
you're
actually
trying
to
measure,
like
the
skill
that
you're
trying
to
measure,
capability
you're
trying
to
measure,
very
difficult.
Um
because
whatever
you
put
together
is
just
a
proxy
for
whatever
that
thing
is,
right?
And
it's
just
one
dimension.
So,
that's
one.
Two
is
it's
very
tedious
to
get
the
answer
key
or
the
way
that
you
grade
this
correctly.
And
if
you
don't
get
the
way
that
you
get
you
grade
the
answers
correctly,
it's
a
eval
that's
very
easy
to
hack
and
very
easy
to
reward
hack.
And
therefore,
you
know,
you
could
score
very
highly
on
the
eval,
um
but
actually
do
really
poor
on
the
on
the
actual
underlying
skill
or
objective
that
you're
trying
to
measure,
right?
And
so,
the
the
the
like
prior
that
I
will
share
is
evals
are
really
hard,
um
not
just
in
financial
work,
but
just
across
the
board.
And
um
what
I
would
say
is
uh
we
don't
think
that
there's
a
really
good
eval
today,
um
for
financial
um
work.
Um
there's
a
bunch
of
existing
prior
work.
I'll
I'll
reference
some
of
the
work
that
we
did,
which
is
a
GDP
eval,
um
which
is
like
a
little
bit
more
broadly
in
knowledge
work.
Um
if
you
guys
look
at
the
Astra
announcement,
you
know,
we don't
talk
about
GDP
eval.
Um
we
we
know
that
the
eval
is
completely
saturated,
uh
and
that
it's
uh
there's
a
and
the
pieces
that
are
not
saturated
are
essentially
broken,
right?
And
so,
we
actually
don't
report
on
that,
we
don't
track
it
anymore.
And
so,
one
of
the
tricky
things
for
um
uh
GPT-6
Astra
was
um
we
didn't
talk
a
whole
lot
about
financial
evals.
We
have
some
internally
that
we
didn't
talk
too
much
about
and
didn't
want
to
share
at
the
time
yet.
They're
coming.
Um
but
it
was
there
was
no
good
way
for
us
to
show
progress
uh
on
financial
tasks
on
these
evals.
Um
there's
a
funny
like
funny
things
like
I
think
there's
this
bias
in
evals
where
if
the
numbers
look
good,
the
researchers
assume
that
the
model's
gotten
better
and
they
don't
investigate
it.
If
the
model
if
the
you
made
a
much
more
capable
model
and
the
eval
numbers
look
bad
or
haven't
increased
in
the
the
scale
that
you
want,
then
you
go
investigate,
right?
So,
this
is
kind
of
like
bias
baked
into
uh
investigation
these
evals.
Something
like
this
happened
with
GPT-6
where
we
we
ran
GPT-6
on
a
set
of
on
financial
evals
and
the
numbers
didn't
really
change
much.
We're
like,
"Oh,
like
what's
going
on
here?
Let's
take
a
look
at
this
eval."
We
we
we
did
a
deep
dive
into
these
different
evals
and
lots
of
things
were
broken.
Uh
we
like
the
basically
we
found
that
we
had
saturated
the
evals
and
the
questions
that
we
were
getting
wrong
were
driven
by
incorrect
answer
keys,
um
poorly
specified
prompts,
or
just
some
other
flaw
with
the
eval.
Um
and
so
all
that
to
say
like
one
of
the
things
that
my
team
is
working
on
currently
is
to
try
to
build
a
much
better
eval
that
actually
predicts
the
ability
to
automate
the
work
of
that
specific
profession.
And
so
yeah,
and
so
the
idea
is
like
we'll
have
something
like
an
investment
banking
eval
that
predicts,
you
know,
if
you
score
well
on
this
eval,
you
could
probably
automate
a
lot
of
the
work
of
a
junior
analyst
uh
in
investment
banking.
Original English
>> We
got
to
wrap
here
soon.
I
want
to
ask
uh
any
callouts
for
people
in
the
finance
space,
the
Latent
Space
audience,
uh
your
team
is
probably
hiring,
but
last
thing
to
put
out
there,
how
how
can
people
be
be
helpful
to
you?
Original English
>> Yeah,
wonderful.
Well,
I
would
say
like
first
and
foremost
like
please
check
out
Chat
GPT
Financial
Services.
Um
it
is
an
enterprise
product,
but
we're
trying
very
hard
to
make
it
available
to
more
uh
prosumers
on
the
pro
plan
and
so
hopefully
we'll
have
some
cool
announcements
there.
Um
two,
yes,
my
team
is
hiring.
Uh
we're
seeing
incredible
uh
customer
traction
with
the
product
and
uh
because
of
that
we're
hiring
and
scaling
the
team
rapidly.
It's
a
very
diverse
team
with
lots
of
different
roles
and
so
I
just
want
to
call
out
a
few
of
them
very
quickly.
Um
there's
obviously
the
the
standard
uh
front
end
back
end
uh
engineering,
so
um
kind
of
traditional
product
building.
So
that
was
one.
Two,
we're
very
much
looking
for
wonderful
product
managers.
I
think
in
some
ways
uh
great
product
management
is
the
the
main
bottleneck
in
trying
to
go
win
in
this
space
and
so
we're
trying
to
hire
wonderful
product
managers
in
investment
banking,
equity
research,
asset
management,
uh
you
know,
across
the
board
we're
we're
trying
to
hire
product
managers.
Uh
and
then
the
other
role
that
I
want
to
give
a
special
shout
out
to
is
we're
hiring
someone
we
call
a
subject
matter
expert.
Um
and
you
know,
it's
really
important.
Uh
one
of
the
things
that
we
did
well
in
in
coding
is,
you
know,
the
the
people
that
were
training
the
models
and
making
them
better
understood
what
good
code
looks
like,
right?
And
that
was
a
huge
tailwind
for
us
as
we're
making
the
models
better
at
these
things.
We
don't
have
that
advantage
when
it
comes
to
making
the
models
models
better
at
finance.
And
so
we're
we're
building
out
and
trying
to
hire
a
lot
of
folks
that
are
able
to
bring
that
financial
expertise
and
work
with
the
engineers,
work
with
the
researchers,
work
with
the
product
managers
to
make
the
model
and
the
product
better
in
your
specific
fields.
And
so
if
any
of
those
resonates
with
you,
like
I
highly
you
know,
recommend
that
you
reach
out
to
me.
I'm
available
on
LinkedIn.
We
also
have
these
job
listings
posted
on
our
careers
page.
It's
pretty
easy
to
find.
Original English
>> Great.
Well,
you
answered
my
question.
I
was
going
to
ask
when
I
when
can
I
have
a
play
with
this,
but
it
is
coming
to
Pro
Pro
Pro
Pro
Pro
Original English
>> very
hard
to
make
it
available
to
more
people.
Original English
>> very
common
opening
eye
stuff,
you
know,
it
makes
sense
you
make
stuff
for
enterprise
and
then
this
trickles
down
the
the
regular
models.
It
comes
to
Pro
plan.
So
I
expect
for
your
general
usage
down
the
line
it'll
get
better
at
console
stuff.
Original English
>> Awesome
ball.
Very
excited
to
have
you.
Check
out
the
keynote.
You
gave
a
lot.
You
gave
good
predictions.
You
talked
a
little
bit
about
some
juicy
we
fixed
pre-training
issues.
So
I
'll
leave
breadcrumbs
for
you
guys
to
go
watch,
but
thanks
for
joining.
Original English
>> Yeah,
awesome.
Thank
you
so
much.