On Curiosity — Sharif Shameem, Lexica

Channel: aiDotEngineer

Published at: 2025-07-19

YouTube video id: 0F8mnGPUycY

Source: https://www.youtube.com/watch?v=0F8mnGPUycY

[Music]
All right. Hey everyone. Uh, my name is
Sharief. I'll be talking to you about
demos and why I think demos are probably
the most important thing in the world
right now. Um, I'm the founder of
Lexica. We're working on generative
models, specifically image models. Um,
but I kind of want to just talk to you
about something a bit more than just
models themselves. Um, even more than
demos. I kind of just want to talk to
you about curiosity. Um, there was a
famous French mathematician Poare. He
said at the moment when I put my foot on
the step, the idea came to me. He was
working on this really really esoteric
field of mathematics called fusion
functions. Um, and he was stuck on this
problem for weeks at a time. He didn't
really know how to make any progress at
all. and he was boarding a bus one day
and suddenly it kind of just all came to
him. He went from not knowing at all to
having a full understanding of the
problem. Uh he said something along the
lines of the role of this unconscious
work in mathematical invention appears
to me as incontestable.
Um I'm going to make one main argument
to you guys today and that's going to be
that curiosity is the main force for how
we pull ideas from the future into the
present. Um, and when we have these
subconscious patterns that our brains
recognize, they kind of surface as a
feeling. And this feeling is what we
know as curiosity.
So, I'm going to present you with a few
demos I've worked on over the years. Um,
and they've each followed a specific
pattern where initially I had this
really great idea. I thought it was
fantastic that it was going to change
everything. And then you kind of get to
implementing the specific idea and you
realize it's actually not possible at
all. And then like through sheer effort
and like determination, you somehow find
a way to make things work even though
you're working with models that have
maybe a context length of like 2,000
tokens. Uh and then once you get it
working, you feel this like really good
sense of pride and joy. Um and I think
the most important thing about good
demos is that um they're kind of a way
of exploring what's possible with these
models. I'm I kind of see these models
as not necessarily things you can kind
of understand fully without interacting
with them. And I think the way you can
best interact with them is by making
really really interesting demos. And uh
the way you make interesting demos is
just by following your curiosity.
So this is from 2020. This was when GPD3
was released. Um this was pretty
mind-blowing for me and I was surprised
no one was really talking about this. Uh
GPD3 for those of you remember had a
context length of 2,000 tokens. Uh it
cost I think $75 per million output
tokens. Um, and yeah, you had to get
specific permissions from OpenAI before
you shared anything about the model. Uh,
you couldn't ship a chat app because
that violated the terms of service. But
it was a really magical time. It felt
like you had this new tool in this like
in this toolkit of computing and you
could do so many things with it. And I
think what was really important about
this demo is that it inspired people
that you could actually do things with
software. Um, I think the way you get
really impressive ideas is actually not
by doing anything special. I think each
person has their own unique kind of
context window, the things you've seen
and experienced. And I just so happened
to watch a talk by Brett Victor before
making this where um he came up with
this principle that creators needed
immediate feedback with what they're
creating. And I was really tired of
copying and pasting code into my editor
and then compiling it and then like
running it and see what would happen. So
I decided to just put like a JSX
compiler in the browser and it just felt
different. It felt kind of magical in a
way. Um, and now today like Claude
system prompt is 25,000 tokens which is
kind of funny.
Here's another similar demo. This one's
a bit more interactive. So you can kind
of describe what you want. And then uh
because the context windows were so
small, it couldn't actually generate the
entire application in a single prompt.
uh you actually had to do three parallel
prompts and then join them in the
background. Uh this is really simple
just asking for a Google homepage and
then it generates three different
components for it. Um but yeah, this is
just I think one of the ways you can
express your curiosity. Uh you kind of
look at the world around you and what
you've experienced and you kind of
synthesize new ideas and you get this
subconscious feeling pulling you in a
direction and I think the demo is the
best way to kind of express that feeling
to the world.
Um, here's another more interesting one.
This was 2021. I think the context
lengths now expanded from 2,000 tokens
to about 4,000 tokens. So, we could do a
bit more with this. Um, I was kind of
curious if these models had any sense of
agency. So, I decided to give it a
really simple objective of buying me
AirPods in Chrome. And, uh, if you were
to just dump a web page into the browser
into the context window, it just
wouldn't work. Like the walmart.com
shopping page would be like 24,000
tokens. It's just impossible. Uh so I
was actually a bit frustrated that I
couldn't get it to work for a few days.
Uh so I wrote a custom HTML parser that
would parse a web page into its core
essence which was able to fit it into
the tiny context window of GPD3 in 2021.
Uh it definitely failed spectacularly.
It got distracted with the terms of
service. Uh but I think it was more so
just interesting that we discovered that
these models pre-trained on web text had
this sense of agency kind of internal in
their weights. Uh, we kind of take that
for granted now, but 2021 was a very
different time.
Here's a more recent demo from a friend
of mine, Farsza. Uh, he's using Gemini
2.5 Pro here today. So, we're still
discovering new capabilities here. He's
making a basketball shot tracker where
he's just putting in a video of him
playing basketball, asking it to provide
feedback as if Michael Jordan was
watching his gameplay. And I think this
is a really great demo because it
inspires people to realize that you can
actually make video first experiences
with Gemini 2.5 Pro. Uh before this it
was kind of like oh you can have it
watch your screen and it'll give you
feedback on your code. But there's so
much more we can do. And I think one of
the main reasons I find demos really
really interesting is that they inspire
possibility. Um, so much so that there's
probably so much lowhanging fruit today
in these models that if you were to halt
all capabilities, if you kept all the
weights frozen, didn't do a single back
propagation, I think you could build
really amazing products for the next 10
years, keeping everything constant. Um,
and I think the way you do that is just
by building these demos and following
your curiosity.
So I have this really famous quote by
Richard Hamming where he says, "In
science, if you know what you're doing,
you should not be doing it. engineering
if you know what you're doing you should
not be doing it. So traditional
engineering is very teological. It's
very goal oriented, very purpose-
driven. Um, but I think AI engineering
is a bit different. I think AI
engineering is actually a bit more it's
it's a bit closer to excavating. You're
looking for new capabilities hidden
within these models. And your toolkit is
a demo. Uh, it your curiosity is kind of
your flashlight guiding you to where the
interesting bits of the models are. And
the way you kind of discover what's
possible is just by making things. Um,
and what's really really interesting is
that even the researchers today at labs
like OpenAI and Anthropic actually don't
have a full understanding of the
capabilities of these models. Um, I've
had OpenAI researchers show me or tell
me that they didn't even know GP3 could
do this uh could browse the web or that
it could generate fully functioning
React components, which was pretty
interesting. Um,
this is pretty funny. Uh Charles Darwin
was famous for coming coming up with a
theory of evolution but little known
fact he actually spent eight years
studying barnacles like the things on
the sides of ships and peers and docks.
Uh he spent he spent eight years
studying barnacles so much so that
people thought he was going crazy uh
before he published evolution. Um, in
the moment you wouldn't have known that
it was important though, but the
barnacle studying taught him that
evolution was correct and it was kind of
indisputable evidence for his theory.
Um, in the moment you actually don't
know what is actually work versus play.
Uh, what you're doing might feel like
it's useless. It might feel like it's
leading nowhere. Um, but sometimes you
need to study barnacles for eight years
before you can publish evolution.
So, I think we're in this really strange
moment right now in 2025. Uh, these
models can do amazing things. There's
tons of them. Their context windows have
now expanded from 2,000 to maybe a
million tokens or so. Um, and I think
demos are the way we explore what's
possible. It's the way we we expand the
search space and kind of see what we can
do with these capabilities. Um, and I
think it's not something you can predict
ahead of time. It's kind of like
crossing a foggy pond. Uh, you kind of
take one stone, you kind of step on a
stone and then see where it leads. If it
leads somewhere interesting, you can
keep going, but if it doesn't, you can
always backtrack and go a different way.
You'll never be able to plan your route
across the pond ahead of time. You just
kind of have to take the first step.
I came across this really interesting
tweet um and I really like it. It's
because Anthropic really markets Claude
as kind of a coding model or like a
general reasoning model, but it's like
trying to sell an intergalactic
spaceship as a toaster because one of
its surfaces gets hot every once in a
while. And I think this is a really
really good way of thinking of these
models. There are so much capabilities
latent in them that uh we kind of only
focus on the immediate and the obvious.
But good demos reveal really interesting
capabilities uh mainly through
exploration and play. And I think
uncertainty is at the core of being an
AI engineer. If you know what you're
doing, you're kind of doing it wrong.
And I think if you're uncertain and
you're kind of just exploring, uh you'll
you'll lead down interesting you'll find
yourself being led down interesting
paths. Um
yeah, in subconsciously you notice these
patterns because you've worked with
things that no one else has worked with
before. Uh your life is unique to you.
Your context window is unique to you and
no one else has that same shared context
window. So when you come across an idea
in your head, often times you're one of
the only people to ever have that idea.
And I think you'd be doing yourself a
great injustice if you never actually
tried to make that idea a reality.
So I'm going to close with this slide.
Um, one of the greatest computing papers
ever written was man machine symbiosis
by lick lighter in the 1960s. And the
epitome of technology at the time were
vacuum tube computers and punch cards.
Uh, if you wanted to write a program, it
would probably take a few hours, maybe
even days to run. Um, meanwhile today we
have claopus 4 on our computers. It's
actually kind of insane. And I think
Lick Lighter genuinely would have killed
someone to have an hour with the tools
we have today. Um, and like I'm not even
joking. I think it's kind of important.
So much so that I feel like today we
have a moral obligation to do him
justice and everyone else in the field
that came before us. Uh, not only to
just follow your curiosity, but to share
what you explore with the world. Um,
because by sharing your demos, you kind
of share what's possible with these
models. And I think that's how we move
the field forward. And um yeah, that's
that's really it. Your unique
perspective shouldn't be wasted, and I
think you have a moral responsibility to
share them with the world.
Thank you.
All right, we've got some time for
questions. Does anybody have any?
None.
Cool. Thank you, guys.
Appreciate it.
We're doing really good for time. I was
going to ask you if you had like other
demos that you wanted to show us because
the I I liked seeing the 2020 versions
of things.
I have a few more actually. Do you want
me to pull them?
We've got eight minutes. You might as
well
as long as they don't use Wi-Fi because
apparently that's the running joke of
this conference.
I I think I might have a few downloaded.
Let me check.
For the people in the room, I did try
that basketball one except I tried to
apply to running and it works really
well and it pretty much gave the same
feedback that my $600 a month running
coach would give me. Oh wow.
And I thought, wait, I think I can
cancel this.
Did it give you like pretty good advice
on your gate?
It gave me not not just the gate per
step.
And so that's something that my coach
would never able be able to do. What I
couldn't get to figure out is um how it
had the little arrow on top of the head.
But if I had 20 more minutes to
Yeah. Here's a pretty cool demo. think
was also from 2020. Um, let's see if
it's playing. It's not. Let me Oh, it
is. Um, yeah, this was about a few weeks
after the GP3 API came out. And I think
the way I came across the API was really
funny. Uh, someone had said to me, you
have to try this out. OpenAI has created
AGI and it's here available today and no
one's really talking about it. And I was
like, okay, let's see what this is
about. Um, and I I quickly realized I
could actually write code, but writing
code in the text interface was not
really the best way to do it. Uh, so you
actually hook it up to an API, put a
compiler in the browser, and you get
this like nice back and forth visual
interface. We kind of take this granted
for today with tools like cursor where
you can kind of like chat with your code
in the sidebar. But, uh, in 2020, this
felt really really different than what
anything was possible. Um, here I'm like
working on a like a really really basic
like banking app where you just ask it
to add $3 or subtract another $5. Uh, it
was pretty funny because like the bugs
were really bad. You could actually
there's a button where you could give
away all your money and if you were in
debt it would just like negate it and
make you make your balance go to zero
again. Um, but this really was I think
the start of vibe coding and it really a
lot of people to take these models not
only as like language models but kind of
reasoning engines. Um, yeah. And I think
I think um the way to think about these
models is really that like they're these
really really intelligent in a way
beings, which sounds kind of weird to
say out loud, but that's like the mental
model I have for them. And you kind of
hook them up to these different
apparatuses and they can kind of work
them and you kind of like instill these
tools with a sense of like uh purpose
and agency. Um, yeah. I I really just
hope a lot more people are inspired to
work on demos because the capabilities
we have today are really impressive and
you'd be really doing a disservice by
not just like building something really
fun and simple and sharing it with the
world.
Yeah. Can over there.
Yeah.
Yes, it was the base model. Uh, we
didn't have an we didn't have an
instruct model until about a year later.
Um, so what it was essentially similar
to base models we have today where you
give it a prefix and it just completes
it. So you you prompt engineer with a
few examples and that's usually good
enough.
Any other demos you got there?
Uh I can I can go into the archive.
Do you want to go through the entire
desktop while you're at it?
Let me close this one.
I I I have a few but I I don't know. Do
we have time? We have five minutes.
Let's see if I can find anything. Um
okay, let let me try something really
quick.
Yeah, sure.
How did
I never
Sure. Yeah. I think um a lot of it was
just kind of introspecting on why I made
these demos in the first place. Um, a
large part of it came from a sense of
frustration that we have these really
powerful models today and no one really
knows what they're capable of doing. Um,
and I think I examined it a bit further
and it did feel like a sense of moral
obligation. Uh, you have these pioneers
of computing uh from the 60s and 70s and
80s like Lick Lighter and Alen K and
whatnot and they came up with these
grand ideas uh with the computers they
had available to them. They just
couldn't make it possible. And I look at
what we have today and it's kind of like
we're spoiled by so many amazing pieces
of technology and we're kind of just
making the same things all over again.
Uh but really I think if you look back
at like what people were writing about
in the 60s and 70s, there's a whole gold
mine of ideas there that we can revisit
and actually make possible today. Um in
the uh man computer man machine
symbiosis paper lick lighter talks about
an assistant that knows everything
you're working on and has like perfect
context and can help you with anything
immediately. Um, and here we have like
chat GBT where every time you want to
talk to it, you press new chat and it
has no memory of what you've talked
about beforehand minus like a few basic
facts. Um, and I think it's really just
it really boils down to wanting to uh
kind of do the ideas that these pioneers
came up with justice beforehand.
Thank you.
Three minutes. So, did you have
something?
Um
um yeah, this was an old GPD3 demo where
the idea was how do you get these models
to solve very large and ambitious
problems. It was called multivac and the
idea was you can't really fit everything
into a 2000 context window token context
window. So what you do is you you
essentially break down the problems into
more digestible sub problems and you
have this kind of visual interface to
help you see where things are going. So
you can give it some really ambitious
problem like how do you solve climate
change and it might come up with things
like convince more people to go
vegetarian or build climate or build
wind turbines and like install more
solar panels and then you can click on
each of the sub ideas and it kind of
breaks it down even further. Um yeah I
think one of the core ideas behind this
was like these models are a lot more
than just text completion models but I
think they can be useful as like very
helpful reasoning assistance uh
specifically at solving big problems. Uh
so much so that they could come up with
ideas on their own one day and hopefully
be really useful thought partners.
Yeah. I mean looking at it now it's
pretty rudimentary but I maybe someone
should make a new version of this with
like Opus Max.
Yeah. I mean someone here should do it.
I think that'd be pretty cool.
Um yeah that's about it guys. Thanks.
[Music]