# Chai Discovery Builds AI Protein Design Platform

**Podcast:** Latent Space: The AI Engineer Podcast
**Published:** 2026-08-11

## Transcript

It looks a lot less like a, you know, a chat GPT and a lot more like Autodesk or SolidWorks or Figma, you know, if you've used those things where you can kind of load up your molecule.
There's this almost like Photoshop-esque like design suite.
You have this equivalent of a paint tool to kind of paint your epitope.
You have this equivalent of a content-aware fill tool to kind of get your binders generated from Chai.
And I think to add to that, right, yeah, this notion of target discovery and hit discovery and optimization where each of these has a gate and takes a few months.
a few years is this very like waterfall model, right, where the cost of trying things and getting things early is very expensive.
But I think to what Matt's saying, right, if you start to get in a regime where you can have models give you really promising candidates, you can start to make that look a lot more like a loop, right?
It's akin to like becoming more agile.
in software development.
But now the next problem is like agonists, right?
Like how do you reliably one shot hitting a switch like on a cell, right?
Or by specifics or ADCs, right?
And I think this levels of abstraction that we're going to have to climb with the product as like the models get better.
If you have like these really good primitives for structure prediction and binding and design, and you can kind of compose them, then you can start to just like grow into like the outer loop of science.
Welcome to Layton Space, AI for science.
I'm Brandon.
I build RA Therapeutics at Atomic AI.
I'm joined by my co-host, RJ Haneke, CTO and co-founder of Mirror Omics.
It's a pleasure to have with us in the studio today, Mac McPartland and Neil Patil of Chai Discovery.
Chai is a protein design startup, which is about two and a half years old and has made quite a splash in those few years.
They have several very exciting announcements that I think they'll tell us about today.
But yeah, to get started, could you two give us a bit about your background and what you do at Chai?
Yeah, thank you very much for having us.
We're super excited to talk about CHI today.
I'm Matt McPartland.
I'm one of the co-founders of CHI.
My background is in like AI, biology-related stuff during my PhD.
I actually started my PhD in like theoretical computer science and then transitioned to this later.
Yeah, I've been doing this stuff now for like...
about eight years and i kind of came into the field at an interesting time where protein structure prediction was like just starting to see signs of life so this is like alpha fold one days um and was in the field during alpha fold two and like i got to see a lot of the interesting developments at that time so yeah i i'd always been pretty interested in like applying this stuff in the real world and chai was just a perfect opportunity to do that And I'm Neil Patil.
I help lead a platform and product here at CHI.
So a lot of the stuff around infrastructure to train models, serve them, and then the productization piece, you know, the design suite that lets you use the models.
I kind of have a more meandering path.
So I kind of got into programming like 15 years ago, making apps in the app store, got really addicted to the dopamine hits you get from that.
And then actually got nerd sniped by robotics and like worked on that for a bit.
Self-driving cars in like 2018, 2019.
Got really jaded and was like, I don't want to touch hardware for a while.
I ended up switching and joining a SaaS company called Vanta.
I was one of the first employees there and kind of grew with it.
Started my own security company afterwards.
Got a few years into that and I was like, you know what?
items are kind of cool.
Like I want to work on something a little more meaningful.
And so I joined Chai about a year ago, right after Chai 2 was announced to help with a lot of the platform and commercialization pieces.
Awesome.
It's like the five stages of grief or something.
Yeah.
We're at acceptance.
Awesome.
You have these, I think, four now big partnerships and raised a whole bunch of money.
Can you tell us a little bit about those partnerships?
And then what I really want to know is what Are you telling investors and customers it is so compelling that they're willing to do these big deals?
Yeah, so we've been very fortunate to partner first with Eli Lilly and then with Pfizer, Novartis, and Argenx.
Yeah, I think...
It's been like a really interesting ride.
And I think our business model is also very compelling to a lot of people.
Like we really like to we care about the partners succeeding like this Chai as a company really depends on how the partners succeed.
I think Neil probably has some interesting takes on like, you know, what we actually offer and what makes that so compelling.
So I'll hand it over to you.
Yeah, I mean, as you all know, drug discovery is a very lengthy process, right?
And a lot of these pharma companies are spending lots of time, you know, years and years and billions of dollars trying to find initial therapeutic candidates.
And so at Chai, you know, we train models that can help accelerate that process and kind of find those initial binders and then some.
And, you know, we, you know, there's a lot of bio companies, AI for bio companies that are like making their own drugs.
We really don't see ourselves that way, right?
We see ourselves as almost a neutral software factory for making.
And so that's what, you know, lets us go then work with and support all of these other farmers in their kind of drug discovery journey.
And so, yeah, I mean, a lot of this capital is just another proof points that we can sort of start to really accelerate that software factory, right?
Go after harder modalities, train bigger models, and ultimately just build what our partners and customers ask us for.
But what is it that, why you and not other structural companies, why are they compelled to?
buy from you the thesis of chai has always been to like be the software and modeling layer which was I think, like, very controversial at the time.
Like, everyone, you know, this play has definitely been tried.
Only two years ago, and it's already, like, a completely different world.
Yeah, it's pretty crazy.
Like, people tried this play for a while.
And I think, like, the models just really weren't there yet.
And even, like, for us, we were taking a risk in the very beginning.
Like, we were kind of banking on the models getting there.
And, like, I had seen early signs of life in my work and our CEO, Josh.
Like, he was on the original ESM papers on that team in Meta.
And he was seeing, like, pretty early signs of life that, like, you know.
There might be scaling laws here.
I think we'll actually be able to start designing things.
Structure prediction is getting really good.
One crazy thought is we didn't have a multimer structure prediction model until 2021.
That was five years ago when we could start with deep learning to actually predict the shape of two proteins at once.
outfold one was like and outfold two was like this huge breakthrough but then like outfold two multimer came out like a year later so like you really kind of needed that to unlock design in the first place anyway like we weren't even trying to predict multiple proteins at once uh and then really like around that time inverse folding kind of started working and it's like oh protein mpnn this actually works in the lab like credit to the baker lab for doing all this really excellent lab validation and all their models but i think like we're starting to see them do interesting things and like actually work on like real-world experiments.
And now is probably the time to start betting on this.
I think like before then, maybe you could take like some experimental data from a campaign on like this one target that you had and you care about, and you might be able to like make some progress on that and like keep hill climbing in this like one very specific case.
General models.
weren't really a thing back then.
So I think like, yeah, we took that bet pretty seriously.
And like, we decided to just like push as hard as possible and to really like shoot for generality in our approach.
And then when Chai 2 came out, our second paper after Chai 1, we kind of like showed the world like.
This is actually possible and it's possible at scale.
We didn't show this for like one or two targets.
Like it kind of works.
Like we were like, let's just go all in.
I think Josh likes to say we set up bold company-wide challenge to design antibodies to 50 targets.
And actually like we saw some signs of life where like, all right, let's like, let's do this with real statistics and see if this actually works.
It's an interesting story of how we chose these targets.
So we were like, all right, what targets are we going to choose?
We should choose, like, some interesting targets, whatever.
And at that point, we were, like, kind of ramping up with CROs and figuring out, like, what does our wetland process look like?
And we decided...
After trying some stuff like mini proteins, whatever, we're like, here are the interesting targets.
This is what we should look at.
And like half the time, the targets just like kind of didn't work.
We were still learning, whatever.
We're like, all right, maybe we should just go with like targets that the CROs have actually validated.
So let's get the CRO catalog, see what they've already worked on, restrict that to like an interesting set.
So from that, we chose 50 targets, designed antibodies against them, got hits to half.
And at that point, I think pharma started to realize like, okay, there are actually signs of life here.
And this might actually.
work in some of our programs.
And so antibodies is maybe a more challenging domain than other structural prediction problems.
So why tackle antibodies?
So maybe back up, what is an antibody?
Yeah.
And what do you do with it?
And why is it an attractive target?
The analogy that everyone gives is like this lock and key kind of problem where like your target, this protein that you're trying to bind to, it might be some like disease protein.
That's kind of like your lock.
And then you want to design this key that fits into it.
And like, in our case, just like sticks there.
The interesting thing with antibodies is like.
these like really flexible, general proteins, like in a lot of ways, they're very general in a lot of ways, they're actually like pretty uniform.
But at least like how they bind to a target is very general.
So like you have a lot of optionality and how you design this kind of binding interface.
The structure prediction problem for antibodies like predict how this antibody actually binds to the target, how it how the key fits into the lock.
that's been a notoriously difficult problem uh the nice thing is like so we've made a lot of progress in structure prediction kind of the field as a whole has come a long way uh along like in in getting structure prediction to where it is but in the design setting you can be a lot more selective about the types of designs you want to make and the types of structures you actually want to focus on and in some cases it might actually be even easier to design a protein binder that is an antibody than to actually predict how it might bind that target in general.
So it's kind of like if you have the freedom to choose, you can kind of just pick the easy cases, if that makes sense.
So the antibody is like there's a whole machinery in the body that works with antibodies.
What does the body do with it naturally and what can you do with them that is sort of not natural but is useful for therapeutics?
This is coming from a non-biologist here, but I think of antibodies, they're these kind of like Y-shaped proteins, so it kind of looks like a P sign with your fingers.
Each of these fingers is kind of like an arm of the antibody.
And it's really actually only the tips of your fingers, the tips of the antibody, that engage in binding.
So this makes these really nice therapeutic design targets for that particular reason.
The nice part is that the rest, apart from the tips, is like...
actually relatively constant so this is called like the framework region of an antibody and the design problem you're typically just designing like the very fingertips and you can actually choose for the most part like these kind of framework regions that your immune system already recognizes so antibodies kind of like these y-shaped proteins that your immune system like recognizes and knows really well it's kind of like your body's it's one of the lines in defense against pathogens and other types of diseases so so i guess uh antibodies can The one end like connects to proteins on the surface of a cell typically or other things, but typically on the surface of a cell.
And then the other end helps the immune system identify.
a pathogen typically.
But you can also do things like you mentioned ADCs, anti-antibody drug conjugates.
So that means putting a drug on the other side or something like that, and that causes when you bind to something that it releases the drug into the cells.
Right.
They're like this very general framework, right, where kind of on the ends you have these CDR loops and you can design them to kind of bind to arbitrary things, where maybe one end you bind to a cancer cell.
the other end you bind to a toxic molecule.
You're now precision delivering that toxic molecule to a cancer cell, right?
Or you just have two ends bind to things and kind of force like induced proximity to have some effect in the body.
Or, you know, a lot of drugs historically are really just like about like blocking things, right?
Like anti-agonist behavior, right?
But maybe you can have agonist behavior where you actually like really precisely like...
press a switch.
Like there's a GPCR protein, which are these like doorbell proteins that sit in your cell membrane.
You have an antibody like very precisely engineered to poke it in a certain way that causes a downstream chain reaction.
And I think like...
One of the things that's really exciting about where we're getting to with some of these models is we can start to get that precise, right?
We can really target a very specific epitope, right?
Meaning like binding spot, right?
A very specific set of atoms to have the antibody go after, which, you know, historically you're, with a lot of drugs, you're just kind of brute forcing, you know, a lot of antibodies and just trying to come up with a bunch of things and see what sticks.
But maybe that gets you a binder to some spot of your target molecule, but that doesn't let you precisely engineer where you're poking after.
I know you're not biologists, but do you have any idea about how they used to design these before, you know, these models came up?
Like, what would you, what was the grueling process you would do to find?
Or what is, which is actually still, yeah, what still is the state of the art in terms of drugs which have made it to the clinic?
Yeah, Josh, our CEO, likes to say that our biggest competitor is the mouse.
So, like, or nature in certain ways.
So, like, traditionally these...
types of like drug-like molecules were either discovered in like these immunization campaigns so like you literally will just like infect a mouse with the disease and see what antibodies it makes to try to like combat that um other ways of doing this is like super large yeast display so on so you might like start with hey i really like this framework and how am i going to like figure out the right loops to design to bind this target i'm just going to try as much as i possibly can and just like literally search for a needle in a haystack and this would be like on the order of like at least billions of potential molecules that you're screening against this one target uh and in that case you might like end up with you know one two maybe like a dozen potential hits to this target you actually you don't know much about those hits all you know is that they kind of like stick to the target you don't know necessarily where like if they're even necessarily drug-like i think like one big separator of chai and like a thing that definitely our partners like to see is like you can be really intentional with how you want to do this this design process you can say i want to bind this target in this particular area you can even go back and look to the designs after like we validated that our designs so you can go back and look and say like is this antibody engaging the target in the way that i expect do i think this will actually have the therapeutic effect that i'm going after one of the cool things about knowing that you have the right binding pose is that you can now also design selectivity into that.
Does your platform have some technique for doing selectivity?
Yeah, there's a nice mix of ideas that went both into the modeling side and especially on the product side for dealing with selectivity and cross-reactivity.
So in some cases, you want your molecule to bind.
uh one target and avoid another one so you might have like healthy variants of protein and like disease variant of protein you want to avoid this this disease variant or you might have some other similar protein that's like not actually harmful in your body that you don't want to just like artificially block so i think like on the modeling side yeah we've come up with ways of doing that but i think it's even more interesting on the product side so like how do you enable customers go through or partners to go through and like actually intentionally design for these things Yeah.
And maybe to like back up and define cross-reactivity, right?
Like it turns out when you're developing a drug, you're not necessarily going straight to injecting that into a human, right?
Like you might want to put it in monkeys first, for example, and the monkey might have a maybe mostly similar, but slightly different variant of it.
And so your drug, you know, not only needs to bind to the human variants, but also the monkey variant, right?
And so, you know, the way we've tried to model the models and the product is to kind of let you account for those very general cases where you say, trying to design something that can bind to both of these things so that I can actually go and develop the drug.
Let me actually identify maybe the region that's conserved and then target.
Conserved means, you know, it doesn't change much between the two and target that exact region.
And then, you know, similarly with...
selectivity, right?
Maybe you might want to, there's a very similar protein in the human that if you accidentally bind that one, that's very bad.
And you only want to bind the target protein.
And, you know, that's why a lot of drugs, right, you know, fail or are toxic or have, you know, really bad side effects, right?
And so it's kind of, you're kind of...
having this like combinatorial problem of like, you know, bind only these things and avoid only these.
And I think what's been really exciting with some of the progress recently has been like a lot of the improvements we've been able to make on the level of specificity we can get to with those models.
So you're not only designing the bind here, but you're also making sure that the It doesn't bind to another thing.
Exactly.
Other ways, like CAR T's have tried to tackle this by having some molecular or some sort of signaling pathway that says if I bind, I only fire if I bind, this one binds and this one doesn't bind.
But you're saying you just design an antibody that actually only will bind to the thing that you care about.
We're getting to the point where in some cases, I mean, it's nuanced, right?
But in some cases, you can actually try that.
Okay, that's amazing.
So you're saying you essentially call it?
counter screen or you have in part of your platform, you can know reliably counter screen against like a large diverse set of proteins, which might be issues for downstream.
I would say the framing is more you can be very specific about what you care about binding versus what you care about avoiding.
But I think, you know, for example, like a lot of the money that we're raising now will let us train bigger models that can maybe be even more general and start to account for even more things at the same time.
Right.
Maybe we should back up.
Let's talk about.
So the history of the Chai, you know, series of models.
Well, why don't you tell the story?
We started Chai around two and a half years ago.
The first couple months, we're like, all right, we're going to work on protein design.
And we're working on this.
We're making some progress.
We're like, oh, it's pretty interesting.
Like, we had some ideas and models.
And then kind of like that was right when Alphold 3 came out.
And we were...
we've like been talking about like, man, we really need like an MSA pipeline.
We need like all of this infrastructure built up.
MSA is multiple sequence alignment pipeline.
Why is this just, we've covered this before, but what is a MSA like in two sentences and why is it important?
So if you want to predict the structure of a protein, it might be really useful to see a bunch of very similar protein sequences.
And what those protein sequences that are really similar tell you is like kind of what positions, like which amino acids end up being conserved across many variants of this protein.
And if you see like...
levels of conservation or like kind of high levels of mutation, like correlated mutations, that typically gives you some indication that these amino acids are close in 3D space.
So you kind of have this like 2D view of a protein, which can then be used to help you predict this 3D structure.
So you're learning from evolution what was conserved because the things that weren't conserved probably broke the protein and something died or didn't make it.
Exactly right.
Yeah.
Yeah.
It's pretty remarkable that this works, honestly.
One of my favorite like bio facts here.
Um, yeah.
So, so we were like kind of thinking like, oh man, it'd be, it'd be nice to have like a lot of infra and whatever.
So alpha three came out.
We're like, Hey, we should, we should like open source this model.
We should just like, you know, bunker down, build all the infra that we need.
Uh, I think like this will pay back like in the longterm for sure of just like as a forcing function to like.
be where we are, and also just like to contribute to the community as a whole.
So it's interesting that you chose, okay, this, we're actually, what we're doing here, we're building a model, but what we're really doing is learning how to build the infrastructure.
Is that kind of what you're saying?
Yeah, that's exactly right.
And like, I had built a lot of like similar infrastructure in my PhD, but not at a production level for a company.
So like at that point, I think we were five people.
five of us at China and we're like, all right, this is our forcing function.
We have like a clear goal to work towards.
It's like very direct.
Let's get this thing going and see how fast we can do it.
You guys were at this time sitting in the OpenAI offices.
We were sitting in the OpenAI offices, yeah, in the mission.
Right.
So like, what's the backstory on that?
It's really interesting.
Two of our co-founders, Josh and Jack, had a relationship with some of the OpenAI people.
Actually, OpenAI.
co-led our seed round.
So we were like kind of thinking like, all right, should we get an office while we're only five people?
And it turned out like that office was mostly vacant.
So we got to sit in on the, like in the OpenA offices for a while.
Chai One, built it, open source, learned about infrastructure.
Yeah.
So then after that, like we really set the sites down on protein design.
And worth pointing out, Chai One was a structure prediction model, right?
So you have the sequence, what is the structure that it folds to?
And then that was it.
Yeah.
Try one.
Try one's finished.
One other crazy story there.
Let's see if we can actually share this.
But this is a hilarious one.
So like we were like, oh, man, we really want to be the first to put this out.
And we're like, OK, we're one week out.
We're like the model is like almost done training.
We're like, should we should we build a web server?
and then we're like oh yeah maybe not and then like we ended up spinning up like this whole web server so like people can use it like rather than just like download the git repo it's kind of annoying especially for biologists and like we actually wanted people to use this so like let's spin up a web server uh let's get the technical report out all this stuff so we we ended up like we were up for like 48 hours straight.
It's like getting the paper over the line, getting like all the last things done on the web server.
And then Josh was interviewing with like Bloomberg TV or something that morning.
And we've been up for like 48 hours straight.
So Josh like runs into a room to do this interview on Bloomberg TV.
And like, I think it was like seven in the morning.
Everyone's in the office.
We didn't want to be seen or whatever.
And the interviewer's like, oh, interesting company.
Doesn't look like there are any employees here.
But yeah, it was a really fun time.
I think the early startup days were just super fun.
So yeah, after that, we kind of set our sights on design.
And really what we were thinking is like...
We kind of always had antibodies in mind.
We thought of this as like the most tractable problem.
The nice thing with proteins is you have this beautiful sequence representation.
There's already a lot of research been done in like, how do you autoregressively generate sequences?
How do you like this sequence generation problem is well studied.
So we were thinking like, what's a nice like area to apply sequence generation to in the biospace?
And it's pretty natural to do like linear sequences of amino acids.
So we start working on design.
a unique thing about chai is like we're not like we're designing antibodies like we're an antibody kind of like we don't we don't really like pigeonhole ourselves into like one therapeutic area so we like try to really tackle this problem very generally so we were thinking like can we design many proteins can we design antibodies can we scaffold regular complexes uh so like really just take a holistic view on like how do you design proteins in general uh and that eventually led to the CHI-2 model.
So that was our first flagship design model.
And that's where the CHI-2 paper and our bold target discovery project came in.
So we designed antibodies to 50 targets for that paper, got binders to about half of them with, I think on average, around a 20% hit rate for binding.
And then afterwards, started working on CHI-3.
So that's our latest series of model, but I'll break there.
But before we talk about CHI-3, can you tell us about...
especially for listeners that may not be familiar with structure prediction models.
What does the model look like?
How does it work in general?
Let's take a look at Chai1.
Chai1 has this like roughly a tokenizer, a transformer.
something that looks like a language model, and then something that kind of looks like an image diffusion model.
And they're all just like stitched together.
The tokenizer is like not your kind of typical like words of X style tokenizer.
This is like, I have a bunch of atoms in a molecule, and now I want to like pull those into what I would call tokens for my like LM looking trunk.
And then that conditions this like kind of big diffusion model, which will then emit the image, which is some 3D structure.
So is it atoms or is it amino acids that are the input?
it's an interesting question as well uh so we we have like all these different input tracks so like one thing about biology is the data is inherently multi-modality in a sense uh you have these this like you know kind of token sequence representation each of these tokens has like a set of atoms that kind of dangles off and then you also have you know some some properties of the different atoms like an atom is might have like a different It might have a different element type, so like periodic table of atoms.
And then these kind of all get bunched together into tokens.
Once tokenized, you can kind of process this in very standard ways.
But then ultimately you have to get back to these like 3D coordinates.
So in order to predict the structure, this is just some 3D object.
And that object goes through, or like to emit that object, you go through what looks like an image diffusion model where you kind of go back from tokens back to the atom representation.
i see so the tokens go in the transformer establishes the relationship between the different tokens and then the diffusion model turns that represent that latent representation into a 3d structure that's exactly right yeah okay great so that's chai two that was try one okay okay so try one folding model yeah it's like uh and Like all this bio stuff, it sounds like kind of scary to like atoms, tokens, amino acids.
Like at the end of the day, my background personally is like theoretical computer science.
That's what I spent like all of my earlier years doing, transitioned to this like pretty late in my PhD.
But I think like the background that you need is really similar to the background that you need for like any other field of machine learning.
There are all these domain specific things that you learn about.
But like one analogy or like anecdote I like to say is.
People think you can't work on like AI bio unless you're a biologist.
It's kind of like you can't work on like video models unless you're like a director or something.
Like there are all these like super domain specific things like, oh yeah, to understand like lighting and a video, things like that.
But at the end of the day, these are just machine learning problems.
And like they're all solved the same way.
Okay, so then Chai 2, there's a jump in capability as well as an architectural change, right?
Yeah.
What we've disclosed about CHI2 is it is an all-atom diffusion model.
So we're trying to predict atoms in 3D space still, but we're doing it in such a way that the model actually has the ability to design atoms, place them, decide which atoms actually are there.
So one way to represent an amino acid, like a protein token, is by which atoms are present.
So in the CHI2 case, we were just predicting, like, all right, show the model, let the model just kind of pick what atoms it wants to keep.
And then map that back to what amino acids there are.
What are you able to do with CHI-2 that you can't do with CHI-1?
Is it just, like, better?
Or are there new capabilities that it brings?
It's design, right?
So CHI-1 lets you say, hey, I know the sequence of amino acids, right?
That text string.
And I know the structure.
That you would get from, like, the genome.
Right.
Exactly.
CHI-2 says, okay, I have a target structure, right, that I want to design a binder to.
Chai 2 will then generate, you know, candidate molecules, candidate medicines that bind to that target.
And so this is kind of a design model or design family of models.
And I think that's where you really cross the threshold of usefulness, right?
Like, I mean, Chai 1 alpha-fold, very useful because you can, you know, you can at least intuit and reason about the structure and see what you're looking at.
But, you know, the ultimate goal here is to design medicines, right, and design new molecules.
And I think Chai 2 really crossed the threshold of performance for doing that with antibodies a year ago.
One analogy here would be kind of like back to the image domain.
So Chai 1 would be like, there is a cat in this image.
They're like, thanks, Chai 1.
And Chai 2 is like, I'll show you a background maybe.
I'll prompt you with some image information like, hey, put a cat in a field.
And Chai 2 will actually just give you back an image of a cat in a field.
And you're like, that's a good-looking image.
Or it's not.
You might have some other model which kind of ranks the image.
But fundamentally, it's the generative problem.
So taking that analogy a step further, it's maybe more like you showed a background and then it generates, there is a cat, and then it generates an image of the cat at the same time.
And it makes sense that there is a cat in this field and also that the cat works in the image.
So it's an interesting problem because you have to generate two things at the same time, both the sequence and the structure.
I don't know if you can, but could you talk a bit about how that works?
How do you do that?
So you co-design the sequence.
in a way that the structure also fits and makes sense.
One way to think about it is kind of like the classic way of doing this.
Let's talk about both and structure prediction.
Like, all right, I know the sequence of like, I can from that roughly figure out the 3D shape.
And then there's kind of like the inverse folding problem, which is like given a 3D shape, give me back a sequence that would fold into this.
And now you kind of like need to do both things at the same time.
But I think like similar principles apply.
Like you can kind of have the model like think a little bit about what should this structure look like.
Then you can have some other part of the model thinking about like, well, now what sequence would maybe support this?
And then like a nice thing with diffusion is like you can do this pretty slowly and pretty iteratively.
So you can give the model a lot of time to think about, all right, if I change the structure like this, how should the sequence?
And you can kind of just play this back and forth and back and forth.
And eventually it ends up kind of converging on something that's self-consistent.
It's almost like an EM algorithm.
Yeah, exactly.
So you have this model now, Chaitu, which is able to predict or to sample a structure and a sequence which generates that structure.
And just because you can generate a structure...
doesn't necessarily mean it's necessarily accurate enough to do something.
So do you have other scaffolding on top of that?
Are there additional problems?
Like, are you one-shotting these things or are you, you know, needing to generate thousands of them and then you have a ranking or scoring?
Or, you know, like just having a candidate is maybe, let's say, not enough.
So what do you do once you sample a structure?
Traditionally, what's done and like when...
co-design and like protein structure design, like started to become a thing.
We're like kind of at a loss for metrics is like, how do you know that your protein, like you designed some, some like sequencing structure.
oh how do i know that this is legit or not like i can tell you it's like anything it's like totally out of domain now right yeah and like as a human you can look at this thing and be like i don't know it checks out like even biologists are like i have no idea if this thing actually folds like maybe some of it looks right uh even our biologists are surprised by the way with like some of our designs that like do end up working What was done at the time is we kind of came up with a bunch of metrics, and AlphaFold really is what enabled this.
So you'd take the sequence that you predicted, you'd run that through some totally distinct structure prediction method.
So this is completely independent of your model.
And you say, if an independent model thinks that this sequence folds to a similar structure, then it has a higher likelihood of being correct than like, you know.
just whatever the prior likelihood would be uh so you can take your sequence now and you can measure like how consistent is this structure prediction method with the structure that you actually predicted for that sequence you can now compare your design to an independent model structure prediction and that became like a really good way of gaining conviction that your design model was correct.
And people kind of like game these benchmarks for a while and kept pushing, pushing, pushing.
It turns out like it's easy to get self consistency, consistent design instructors.
If all of your proteins look identical, there are a lot of problems that this creates.
But then people started adding more and more on top of this.
Yeah, that is that's an interesting point that I think some people have acknowledged in the community.
So how did you solve that?
Yeah, you can see that if you sort of use your.
Oracle and also your sampler at the same time, you eventually will converge.
What do you do to stop that or to convince yourselves that you're doing something valuable?
One of the nice things about structure prediction methods is that usually you have some calibration how.
kind of how confident the model is in its prediction.
It turns out these models, they can give you a pretty well calibrated confidence prediction.
So rather than just say, this is what I think the structure looks like, I'll say, this is what I think the structure looks like.
And kind of like, here are the parts that I'm not really certain about.
And you can kind of aggregate this down to like a single scalar.
And typically what people do is they'll look at like, okay, like not only how self-consistent am I, how much does this independent folding model even like the structure that it output?
So that was one way of.
early on I'd say to like just gain confidence and then like another thing that people often do is they'll look at like the diversity of their generations because again you could have a model that's perfectly consistent gives you great confidence predictions back might be the same structure every time like same sequence every time so you also want to see like okay how diverse are the solutions how many of these new problems can I solve in a sense if I had a lot of a whole lot of money to validate how would you do that can I go and you know, do cryo EM or something like that and try to figure out the structure, you know, sort of get some ground truth on that.
It's more that the feedback loop is really slow.
So you can validate a few structures like this, but it might take months.
And it's just not like a very scalable direction.
So I think that's like a problem for the field as a whole.
And I think people are spending a lot of time, even like especially at Chai, I think thinking about how do we validate these problems at like bigger scale?
How do we, you know, basically increase the throughput of our validation or increase the cycle time?
Because if you're waiting months to figure out, hey, was my model correct?
Like it's just, it's hard to iterate in a research environment that way.
The good news is that this is getting a lot better, right?
Like there's a whole network now of wet labs that you can work with that will run, you know, these assays, these experiments and tell you things about, say, you know, does your protein that you came up with bind to its target well?
And so, you know, thankfully we're not at years, right?
We're down to like weeks, which, you know, not as fast as like LLM land where you can just, you know, scale up and eval with and throw more compute and get results back in hours.
But, you know, fast enough to where you can start to recursively self-improve.
And, you know, I think we also...
spend a lot of time like, you know, figuring out what are the metrics that we can compute, you know, in silico, like on the computer that are predictive perhaps of lab success.
But, you know, your question about cryo-EM, yeah.
I mean, also, you kind of have to measure the structure.
And as you know, that's like so expensive because you have to kind of freeze the protein and shoot these electron beams at it and see how they bounce off.
I remember there's like this really funny anecdote.
We'll see if I can share it.
But like the, you know, the paper in Chai 2, we actually, you know, did that.
We took some of the, you know, the proteins that the model predicted and ran cryo-EM and we got the results back.
And we're like...
wait, the results look wrong because we had overlaid the kind of prediction over the point, the electron cloud, the point cloud.
We didn't see any difference.
And point being, like, we're getting the point now where these structure prediction models are within, you know, a few angstroms or less of the actual atomic positions that you validate.
And in this case, it was a 0.33 angstrom error, which is one third the width of an atom.
And we're like, this, like, can't even be right.
Like, clearly they just sent us back their own design.
They just sent us back our design.
Yeah, exactly.
Did you check for data leakage?
Yeah.
In this case, we actually chose these targets specifically to have no known antibody binder.
So if we did get a hit, it was definitely the first antibody hit to this target.
I think that's one of the things I didn't realize about biology was like just how much of it is literally feeling around in the dark.
And that's not even a metaphor.
You literally can't see like how these things look, right?
So structure models are so, so huge because now you can, okay, you can actually predict within an atom, you know, how these things look.
And that enables you to then do things like Chai 2 with the design models.
This to me is AI for science is one of the cornerstone problems, right?
You don't know, you fundamentally don't even know how to aim.
measure your problem yeah in a lot of cases so it's very difficult to validate yeah so you you're getting these sub angstrom predictions with chai 2 chai 3 what why chai 3 what's better or what yeah i think like with with chai 3 so like honestly like there was a chai 2 there's a chai 2.5 there was a chai 2.7 there was a eventually a chai 3 and like each time we saw better and better performance Uh, and I think like the, the main thing with try three is like, we look at try two and like, we look at the targets it can solve.
There was like a lot of internal discussion, uh, after try two, like, Hey, we made like successful molecules binders to half of these 50 targets.
Uh, what about the other 25?
You know, what can we do to make those better?
And then like, you know, we were split.
We're like, all right, should we like study these targets that we missed and like figure out exactly like, are there properties of these that we can look at?
Uh, or should we just bet on the models?
Like, will the models just get there if we put more time into, like, you know, just be bitter less and pilled in that sense and just really bet on the models getting better?
And we definitely took the latter approach.
Like, we bet on the models getting better and we just pushed as hard as we could on that front.
So you're scaling up the model, the data, whatever, to just build more accurate models?
Yeah.
Is it accuracy?
Is that the main thing?
Is it binding affinity?
What do we...
So I think binding affinity is a big one.
Like you can't just bind weekly.
In order for this to be like a useful tool, especially for our partners, we need to start producing molecules that are like at or very close to therapeutic grade, which means like they have to bind really tight.
They also have to be developable.
They have to have like all of these nice therapeutic properties.
And developability, I think that we talked about, he mentioned CHI 2.5, right, which we released like a few months after CHI 2.
There was a study we did on the developability of the molecule, which, you know, for the audience, like, Obviously, the molecule has to stick good and stick tightly, but, you know, there are these other properties you care about.
And to use the non-biological terms, right, is it safe?
Is it stable?
Is it easy to manufacture?
Does it, you know, self-aggregate?
And we've been pleasantly surprised at, you know, how much we've been able to climb and push the performance in those areas.
One of the reasons that you want to do antibodies is because the developability.
Yeah, you get a lot for free there, right, with that antibody framework.
Yeah.
It's interesting.
I mean, to me, there are many structure prediction molecules out there.
I mean, models out there.
I feel like it's these other ancillary factors, actually, that are going to probably be the most impactful and the usefulness of a product.
Yeah.
Right.
Yeah, absolutely.
the nice thing about structure prediction is uh there is a ground truth that you can compare against for design you don't really have that.
You're like, here's some new disease molecule.
Give me a binder for that.
And if you want to know if this thing really binds, you have to send it off to the lab and wait a while.
For structure prediction, you can be like, all right, the model hasn't seen this sequence before.
It's never seen anything close.
Does it actually fold up into the correct shape?
And we can just kind of hold that out of the data set and check.
So I think I've always thought of structure prediction as this really nice speed run kind of benchmark to validate ideas on.
Right.
Sorry, I didn't mean to say, I meant, you know, sort of structural models in general.
Yeah.
But yes, exactly.
So maybe we can talk a little bit more about start getting into the product side of things.
Thank you for coming.
Actually, I mean, like I said, I really think this goes throughout not only for, you know, sort of structural models like this, but also virtual cell and whatever.
It's really all the other stuff around.
the drug development process that is going to have the biggest impact.
So you talk a little bit about that?
Yeah, I think that's actually a good thing to talk about after Chai 2 because I think Chai 2 is where it's started to get really fun from a product perspective, right?
I think with Chai 2, we crossed the threshold of usefulness where after we, you know, released that paper, we had a lot of, you know, you know, pharmas and biotechs approach us and say, hey, this model might be able to do some stuff for us.
Like, can we use it?
And then we're like, oh, man, like we should build a product, right?
We should build something to let you use that model.
And that's right around when I joined.
And there was sort of this, you know, mad, mad build out to both, you know, build the product, which we can talk about the shape of, and also go and secure the compute, actually, so we can go and serve those models to our partners.
And, you know, I think another third piece there that was really interesting is, you know, around security and IP, right?
I think we want to be a very neutral platform that anyone can design medicines on.
But as you guys know, like pharma is this notoriously IP sensitive industry.
Right.
And I think when I joined, a lot of people told me this can't be done.
Like they're not going to put their data in a platform and like have all their new medicines be generating out of it.
And having a bit of a background in security helped a bit.
Whereas like, no, actually, if you like.
just are really aggressive about how you like segment data and set up like single tenancy where you're like almost deploying a separate version or separate account in the product per customer.
You can actually like build a platform and then go and ship it to them.
And so, you know, through the summer of last year, we started doing that, right?
And, you know, we'd been working with, you know, or talking to Eli Lilly and, you know, they were, you know.
One of the first partners to really work with us closely on that.
Kind of, you know, made that V1 of that design suite, right, that you can use to engineer some of those molecules on.
And, you know, maybe it's worth talking a bit about that design suite, right?
I think...
You know, I think we have these really, really powerful models now, right?
That can do like all of these crazy things if you condition them in the right way.
If you kind of give them the right context about, you know, the structure that you're going after or maybe the constraints around the model, right?
Like, hey, I want to design an antibody that hits this GPCR protein, but, you know, doesn't collide with the cell membrane and also targets the specific epitope on that as well.
And, you know, we looked at it and we're like...
I guess we could put a chatbot around it.
That'd be like really easy to talk to.
But like really like you're trying to build something almost very visual, right?
And you can finally build something really visual with some of these structure prediction models.
And so if you kind of look at the Chai product, it looks a lot less like a, you know, a ChatGPT and a lot more like Autodesk or SolidWorks or Figma, you know, if you've used those things where you can kind of load up your molecule.
There's this almost like Photoshop-esque design suite.
You have this equivalent of a paint tool to kind of paint your epitope.
You have this equivalent of a content-aware fill tool to kind of get your binders generated from Chai.
You, of course, have a lot of the scientific analysis and plotting and whatever to understand.
the results of the models.
But we've just been surprised at like how much complexity is actually just in like doing that right so that you kind of don't shoot yourself in the foot when then you're then prompting these models to give you findings.
So are you sitting with people who are designing these antibodies, you know, and feel like they're complaining to you or whatever?
Yeah.
How do you convince med chemists to use your tools?
Because med chemists hate.
AI tools.
Like notorious, like, I don't want to touch this thing.
Or like, I don't understand it.
And they will not touch things, which they do not understand.
Well, it helps a lot to have the models working really well, right?
So when we, you know, when we had the results of CHI 2 and CHI 2.5, I think, you know, that's enough of an activation energy where, you know, pharma companies and scientists in these companies are like, Oh, let's try it.
Actually, can you guys just try running the model against a few of these targets and let's look at the results.
And then we do that and the results are good.
And they're like, OK, let me let me try to get on that product and let me try to use it.
No, I think pharma is like incredibly pragmatic, actually.
Like I've been very impressed with everyone that we've we've worked with so far.
They're very, like I was saying, pragmatic about this, and they're willing to be proven wrong.
And I actually don't blame them for not trusting the models.
I have used these models.
They've been burned so many times.
Rightly so.
I am pretty skeptical when I see any release.
I always have been.
So you really just need to show them the proof.
And they can give you this target that they are interested in, or maybe it's more of something they've worked on in the past they probably don't want to like.
share ip right out of the gate but they can be like hey you know i've had trouble with this particular target in the past let's see how how you guys can do on this and then once you show them the proof they like almost overwhelmingly are willing to accept that I come from a cybersecurity background or, you know, have worked on security products before.
And those were dark, dark years because you spend a lot of your time actually selling to people who are surprisingly not that technical.
You think cybersecurity people are very technical.
In many cases, they are not.
And it is this kind of like uphill enterprise slog to this very unsophisticated customer.
I think we've been just pleasantly surprised.
I have by just how much I enjoy working with our partners and our customers.
You know, these are scientists who have been spending, you know, 5, 10, 20 years of their life working on one target, right, often in some cases.
And they've studied everything about it.
You know, they're very sophisticated.
They're very smart, right?
You know, getting to collaborate with them is just a goldmine.
And we learn a lot about how to make the product better.
You know, there's this anecdote.
We, you know, a few months ago, we were actually showing some of the results that we, from a target that with a pharma partnership.
And one of the scientists in the room like started tearing up and crying.
Oh, wow.
And she was like, and we were like, what's wrong?
She's like, no, I've just been, I've literally spent 10 years trying to get an initial binder to this thing.
And you guys were able to help me do it.
And, you know, that feels really special.
To answer your question, you know, we, you know, there's, of course, the teams of scientists and computational biologists that we're working with within, you know, each of our partnerships.
There's also the people we have within the building, right?
So we, I think one of the things that I really appreciate about CHI is how cross-disciplinary it is.
Like, you know, we have people who are maybe engineering experts and less bio experts like myself.
We have great, you know, AI scientists or ML scientists, but we also have a bunch of scientists that we work with and have joined CHI to sort of help us both, you know, test the limits of the models, right?
See what is CHI-2 actually capable of?
What targets can it do?
What can't it?
Inform some of the research direction there.
I want to add to that.
In the Chi-Ti days, we kind of started with a bunch of engineers and people who have AI bio experience.
We didn't have a hardcore lab scientist.
And one of our first hires on that realm was Nathan Rollins, who...
I think he started working in the Baker lab at 14, graduated from Harvard at like 18 and got his PhD by like 21 or something like this in the Marx lab.
And he was like super skeptical about Chai at first.
And then, you know, the results started to come in.
He's like, okay, this is kind of interesting.
Like this could work.
And then like once the Chai 2 results came back, he was like, I need to bulletproof this.
Like nobody celebrate yet.
So I think like it's been really nice to have that level of rigor.
have people who have really, like, they've spent the time in the lab.
They've designed proteins themselves.
They've literally, in the case of, like, Andy, led several therapeutic programs, brought drugs to the clinic themselves.
And, like, we have all these people internally at CHI just, like, using the products and, like, really battle-testing that.
So if you don't have your own platforms, right?
So you don't have your own programs, right?
You're a pure platform or partnership model, right?
Yeah.
How do you battle-test something if you basically...
you don't have a use case where you have to continuously push it forward.
Or if you are just pushing things forward, when you just end up with your own candidates, if you're successful, and then what do you do about that?
I mean, we have benchmarks of our own internal cases, right?
You know, there's a set of targets that, you know, have our known therapeutics, right, that have known therapeutics against them.
There's a set of targets that we pick to sort of push ourselves, right?
And so we're constantly refining that set and adding to it.
And that's what that internal science team that we have helps with, right, is expanding that and almost running the experiments to try to get initial binders there.
We don't care about going and developing those drugs.
Like, we just do that in service of validating and making our models better.
And then, of course, there's a loop with our partners, too.
Would you consider yourself hit discovery or are you, I guess, using some jargon, hit to lead, lead optimization?
Like, where do you live in this?
And, you know, hit discovery might be like one part of it, which you can do hit discovery.
But the later, the other parts of this are, I think, oftentimes much more bespoke and kind of special.
I mean, how do you balance that?
And it seems much more difficult to me to be general than it does to.
to solve general lead optimization than it does to solve, like, a discovery?
I think ideally, like, we really want to be able to, rather than think of this as a bunch of stages, I think part of the reason why we think of it that way is because the initial molecules are usually, like, not good enough to be drugs.
And, like, really, like, we're kind of at the inflection point now.
We're really seeing this internally at CHI, where the models are getting pretty close to, like, producing molecules that could eventually, or, like, are very close to drugs.
Um, so we, we try not to make too much of a distinction in between, okay, head discovery, lead optimization, all of the different parts of this kind of preclinical pipeline are, are like, you know, the, the light, the North star is to just really produce drug-like molecules straight out of the models.
Of course, this is going to be hard and like, they're going to be like tons of roadblocks and like, you need to be able to like actually prompt the model to do this.
You need the whole RL stack to like learn different properties, things along those lines.
Uh, but I think it's very achievable.
Yeah.
And I think to add to that, right, yeah, this notion of target discovery and hit discovery and optimization where each of these has a gate and takes a few months to a few years is this very like waterfall model, right, where the cost of trying things and getting things early is very expensive.
But I think to what Matt's saying, right, if you start to get in a regime where you can have models give you really promising candidates, you can start to make that look a lot more like a loop, right?
It's akin to like becoming more agile in software development.
Internally, we kind of have two.
you know, North Stars, right?
And at first pass, they almost sound like contradictory, but, you know, the North Star in research is to start to de novo one shot, you know, better and better and better medicinal candidates that are as close to being ready for, you know, the next phase as possible.
But, you know, also within product, we do want to sort of expand into whatever these iterative workflows look like, right?
Where maybe I get a binder, I get some results from the lab, I'm using that to condition my next run of the model.
And I think, you know, They sound contradictory, but I think they're actually not, because I think what's going to happen, you know, the research is going to get better at identifying a de novo candidate for like a specific class of drugs, right?
Say like anti-agonists, right?
Like blocking things, right?
A little bit easier, maybe.
OK, we can get to a state where we can one shot pretty good drugs there.
But now the next problem is like agonists, right?
Like how do you reliably one shot hitting a switch like on a cell, right?
Or bispecifics or ADCs, right?
And I think, you know, there's kind of this.
levels of abstraction that we're going to have to climb with the product as like the models get better.
One of the things I was, I got very existential like a few months ago because I was like, man, all this stuff we're building in the product to like visualize molecules and do this, like maybe I'm just going to have to throw it all away when like Matt ships like Chi 4, right?
But, you know, I think that's kind of the reality of like building products now, right?
You're actually...
using them less as an end in and of itself.
Like maybe you'd have built software that was supposed to last like 20 years.
Now it's supposed to last maybe one year, but it is the bridge to deliver value and kind of enable the research that then gets you to the next thing.
And so I'd imagine we're probably going to rewrite our products at higher and higher levels of abstraction, right?
Like maybe like right now we have something a little bit more akin to cursor where you're...
you know, inspecting the molecule in the same way you're inspecting the code because you really need to verify like the bonds that are forming and the properties of the things that you're getting.
But then, you know, you get to a point where that stuff is solved enough where now the product is actually just helping you orchestrate these like campaigns of hypotheses, right?
Or maybe you have like one target and you're like...
orchestrating a bunch of different epitope choices or whatever against that.
And then maybe you're going up one level of abstraction where you're now doing a whole campaign against all of the targets within a pathway, right?
And I think what's really exciting about that is if you have like these really good primitives for structure prediction and binding and design.
and you can kind of compose them, then you can start to just like grow into like the outer loop of science, right?
And then, you know, maybe the thing runs itself and you start to really get to some really, really, really cool drugs at the end of it.
I actually want to push on what you just said about epitope prediction, because I think a lot of people in the field would argue this might be the much harder problem than finding antibodies and binders.
Where do you think that the state of the art is in general and also with regards to chai in terms of epitope prediction?
And like, is this a problem which has a reasonable, solvable time horizon?
Oh, and also maybe can you define epitope prediction?
I'll think of this at like some different levels.
So the most basic level is, OK, I have some disease that I want to target.
What proteins are actually responsible there?
Like actually figuring out biologically what's going on, like what should I be targeting in the first place with the drug?
Because once you figure that out.
it's kind of like a structural biology problem at that point you're like all right this like set of proteins is responsible and like what's going on there well this is interacting with some other protein that it shouldn't be interacting with and conventionally you just like want to block that interaction or something with anybody but that's kind of where these proteins interact and like the type of interactions that you want to disrupt that's typically like the epitope it's like the actual site on the protein that you want to block This is a ridiculously hard problem.
I'm with you on this.
This is like the harder problem.
Like just the amount of context that you need and like the global understanding that you need to get in order to like actually figure out what's interacting and how.
But maybe let's take a few specific cases.
Let's think about what about SARS-CoV-3 comes around or the new flu or whatever.
What would you do there?
I mean, is that something that you think you could actually reasonably tackle?
In that case, like, yeah, you could just run a structured prediction model maybe and like see where the model thinks this thing will bind.
If it's highly confident in that, you might say, okay, here is like the site that we want to block.
I think in general, still very hard.
And even like structure prediction, it's getting really good.
And like a lot of people think outfold to like solve structure prediction.
Not really.
Like outfold to got like, I think 11%, the multiple version of this got like 11% of antibody antigen prediction cases.
Correct.
That means 90% of the time it's wrong.
Yeah, I mean, but AlphaFold2 solved a certain class of monomeric proteins with MSAs.
Absolutely, yeah.
So, I mean, the MSA, I think, might be the key point here because MSAs are sort of the magic which makes it all work.
It's a template in some sense about what the structure should be.
And antibodies almost...
evolutionarily can't have a template, right?
Everyone has to have unique antibodies custom to the things that they've experienced over the course of their life.
Yeah.
And just to clarify, I had to understand this myself, so maybe I can help the listeners who aren't familiar.
An antibody, the whole point of an antibody is it can be used by the immune system to identify new things that the body hasn't encountered before.
So the design of antibodies as opposed to other.
types of proteins is to the system is designed so that you can quickly recombine different components of it in order to match proteins that are from unknown pathogens, more or less.
And so this is why it's not conserved in evolution the way that other proteins are.
Yeah.
So back to the epitope prediction problem, I think it's still hard.
I think there are a lot of cases that are maybe tractable.
But I think in general, like if you want to discover this for a new target, still a really difficult problem.
Maybe virtual cell would be like the closest thing to state of the art there.
But that's still a ways out.
I wanted to dig in a little bit on the product because there's something I don't understand about the economics of basically all.
all the structural stuff that's happening right now.
And obviously a lot of people think it's very, very valuable.
So there's, you know, I'm not grokking something, but when you look at the cost of developing an antibody, you know, it maybe is a couple million dollars, right?
When you go from...
you've identified a target somehow, and then you say, okay, I need an antibody to match this, and then I have to sort of optimize it in various ways, and then maybe I try it in, I mean, with antibodies, you go to the animal typically faster.
If you look at how much does it cost to bring, if you like are prescient and pick the right target and the right technology to get all the way to drug, it might be half a billion, typically that.
$2.6 billion number is amortized over all the failures as well.
So if you look at just the cost of that one success, depending on the disease, maybe less, but, you know, half a billion might be a good median number or something.
So you're saving like a couple million dollars in a half billion dollar campaign.
So why is this so attractive?
I would maybe challenge the premise a bit, like in a few ways, right?
Like, okay.
Sure, if you're trying to get an antibody for like a very simple kind of target, like maybe, right?
But I think what we've been most excited by is our partners using antibodies in, you know, more sophisticated ways, right?
For example, in CHI-2, we showed like GPCR agonist activity, right, where you can really hit the switch on a, you know, on a cell doorbell protein, so to speak, right, in a very precise way.
Very, very, very hard to do that with antibodies if you can't be that precise, right?
So you're unlocking a new capability.
Yes, right.
I would think about it as less like, oh, I'm taking the existing drugs that I can do and making them faster.
I mean, there is some of that too, right?
But it's like, no, they're just like...
Hey, how do you go after like better targets, right?
That are, you know, maybe more precise, more effective, right?
I think like also on top of that, too, is like there are drug modalities that you just can't discover with immunization.
Like you're not going to design your like crazy, multi-specific, warheaded, super intense formats.
These are really things where you kind of have to design these from first principles, even just with bi-specifics in particular, like both arms need to now bind different targets.
And you've kind of like have this multiplicative effect on your binding rate.
So like if you have a one in a billion chance of finding a binder in arm one, and a one-a-billion chance in ARM2, this just isn't going to work for the traditional approach.
Exactly.
I think the other thing I'd think about is, right, you're not just helping your partner with maybe one drug, right?
There might be a portfolio of targets that they're going after, a portfolio of drugs that they're trying to make.
And the nice thing about the platform approach, rather than that we're developing individual drugs, is we can sort of scale with them as they pursue more targets in addition to more ambitious targets.
So it lets you concentrate your...
you're learning, you know, subdomain of that.
And so that you, everybody benefits from that.
Exactly.
That's the, but okay.
So I didn't, so what are some of these capabilities you mentioned a few?
Are there more that are really interesting that you guys are chasing?
Yes.
I mean, and we talked about like, you know, cross reactivity.
We talked about selectivity.
We talked about some of these like really interesting additional modalities with bispecifics, right?
There's a set of things that you know, our partners have been asking us for that we've been working on that I can't get too into because then that starts to reveal some of the targets that they're going after.
But I think the point being, you can just, once you get precise, like you can start to do some really, really cool drugs.
It's a new technology, right?
So like the technology in...
Pharma means like how do you deliver your therapeutic?
And so this is maybe kind of thinking about like CAR-T is a technology, right?
And so this is maybe a new technology in the sense that you can have these highly, highly engineered.
Right.
And that comes, you know, from the mission of the company is to really turn, you know, drug discovery from a scientific experiment to an engineering discipline, right?
How do you sort of get to the precision engineering phase for biology?
where you can start with, you know, almost declaratively define the thing you're trying to get and have the model fill in the gaps and get you that.
So what is the biggest blocker from going from science to engineering?
Oh, man.
There's so many things.
Like, that's the thing about, you know.
Microheterogenicity.
Yeah.
Microheterogenicity.
What is that?
I don't even want to talk about this.
Like, the amount of headaches.
Too late.
You already met.
Probably not.
You're getting it out.
Okay.
So, like, just like when you're actually parsing, like, first of all, file formats for biologists.
Like, they just don't care.
There's, like, no standardized.
There are standardized file formats.
Are they the best?
I don't really know.
But there's, like, also just, like, a lot of information that you want to pick.
I have this structure.
Here are the people who solved it.
This is the method I used to solve it.
There's like a lot of stuff going on.
And then depending on the method that you use to actually figure out what this 3D structure is, you might have like multiple copies of that structure.
Part of it might not have really been resolved.
You're like, it could be here.
It could be there.
I'm just going to give you like both options.
So like the actual just parsing problem on the engineering side of like working with this type of data is like really difficult.
This seems like something that LLMs can excel at though.
They don't know all the edge cases often, right?
This is more back to just like a simplicity approach.
Like LMs are very good.
I will absolutely give you that.
Then you're thinking about like, do I really want to like, should this function have 20 special cases or should we be like really principled in how we approach this?
And should we be, I guess, more of a...
Opinionated.
Opinionated, yes.
Like how opinionated should we be in how we do this?
We want a strategy that's easy enough for humans to understand.
And like when we're reading through the code base, we really need to know what's going on here.
what are the potential problems?
And like sometimes it just comes down to looking at examples.
But then I think, okay, once you've kind of figured out all the infra work and how you get data into the models, there's then like scaling the model.
There's then scaling the infrastructure around the model to train bigger and bigger versions of this.
And that's like a lot of work that Neil and the product team actually leaves.
Yeah, I mean, that would have been my answer is the infrastructure part.
I mean, you know, not to beat a dead horse, but compute, right?
Getting the compute and using it in the right way is...
such a challenge, especially for startups.
This has been such a theme.
Anthropic is holding back science.
And to that point, we...
I mean, they're also accelerating science, but it's like this weird...
No, totally.
One of the things that I help a lot with at Chai is buying compute for the company.
Worst job, man.
I would not recommend it.
It is very stressful.
But, you know, even September of last year, right?
Back to the hardware job.
Yeah, I know, exactly.
In the wrong way.
But, you know, September of last year, we started to really notice like things are getting tight, right?
We were doing a lot of our inference on, you know, spot and on-demand markets.
And we'd have these days where you just like get these capacity crunches and we're like, okay, we should probably start to get ahead of.
buying some compute for ourself.
And I mean, I think everyone probably says this, but man, it was hard.
Like, I think I didn't realize how much of a power law, you know, this is, right?
Where, you know, there's say 10,000, you know, B300 units that are shipping everywhere, right?
The hyperscalers and the, you know, the biggest AI labs are buying 95 plus percent of it, right?
And then you kind of have the startups like fighting over the scraps.
And I think the other thing that's really interesting, especially if you look at these later compute versions, right?
The Vera Rubins or, you know, the B300s, like a lot of this stuff has been built very like LLM forward, right?
Like you have these, you know, systems with like huge KV caches where you have like 72 GPUs that are all acquired to talk to each other, right?
And, you know, obviously some performance gains there like help us, right?
But like, it's kind of interesting just how much the compute market has kind of gotten LLM pilled.
I think there's like...
a whole probably set of, you know, compute stack and inference optimizations and things that need to be made for this class of models.
And, you know, I think this class of models is going to be like just as big, just as impactful as LLMs, but it's almost like the compute market like kind of doesn't realize that yet, both in the capacity sense, but also in like the software stack sense.
So we actually spend a lot of our time, you know, even just like doing basic optimizations of compute to like get them to work better for the types of models that we have.
Yeah, I know that Some structured models are more recursive than LLMs, for example.
And so that, which changes sort of like maybe the compute to memory ratio that you need and things like that.
What are some of the like sort of cool or interesting optimizations that you've done there?
Depending on the type of model.
So like we can go back to like a try one type model.
In that case, we're following the L fold.
two three architecture and there you're like rather than doing attention over like this like normal sequence representation you're in a sense loosely doing attention over this pair representation so you can think of this as like a sequence of length l squared uh rather than like typically length l if you're doing attention over that the way that you actually batch this up it ends up being l cubed now you're you're in like a pretty pretty heavy compute regime uh so the amount of flops that you're putting into every token stays it's pretty high the amount of memory that like the memory bandwidth uh like overhead of just transferring that from SRAM to whatever, that's a real bottleneck in these architectures.
So even something as simple as a layer norm can take a long time, actually.
That can be a significant amount of the compute that you're using.
So I think on our side, we've spent a lot of time just optimizing and engineering, taking engineering very seriously so that these operations are at least better.
We're always looking at how do new chips perform compared to the older versions.
Sometimes that's even different for training versus inference.
And like, of course, Neil knows this really well.
Well, so there's, you know, what you're doing on the individual GPU.
And then there's like, how do you like orchestrate fleets of GPUs, right?
And, you know, you basically shard your computation, right?
And so, you know, when you're designing a molecule on Chai, it's not necessarily like one call, right?
It's a lot of GPUs being thrown at the problem, right?
Across a lot of compute.
And actually, I would say that one of the hardest things to get right in software engineering is durable execution.
Are y'all familiar with that term?
Can I go on a little?
Ultimately, if you're like computing a lot of data, you know, model calls across like a very wide set of infrastructure, you always run into these problems where like.
some part of the infrastructure is flaky, right?
Like maybe the bucket you're grabbing your data from like goes down or like your database has a blip because there are like too many transactions against it or you're like GPU errors out, right?
I've been at companies before where you like spend so much of your time just dealing with this shit, right?
Like you're basically putting like all of these cues and like all of these retries and you're like duct taping things together and you have a, and it becomes this mess where now what used to be like a, ideally like a pretty simple like computation that's.
distributed, you're ending up spending like 95 plus percent of your time on all of this queuing and retry stuff, right?
We're huge fans of this company called Temporal.
Basically, you know, there's this idea like, look, if you're just trying to get something, a really long running job to run, at the end of the day, what do you need?
You need a queue.
You know, you need your flaky thing like pulling off of the queue.
You need some retry logic to put things back on the queue if they fail, right?
And then you need some whole like orchestration system to just like tie all the cues together and monitor them.
What's really cool about Temporal is like this is a tech, a company that's kind of invented a framework for doing this.
And one of the I think one of the technical decisions we made early on that was very helpful was to run as much stuff as we can on Temporal.
Right.
So whether those are, you know, calls out to the database from the app.
Right.
To make sure the database transaction goes through without failing.
OK, let's have side effects like sit on Temporal so that they get retried smartly without us having to like write our own cue logic.
Right.
Or things related to model calls.
or things related to orchestrating really long data pipelines.
Point being, like, you know, one of those primitives, like just like, hey, you need to get durable execution right so that you're not stuck in like retry hell.
A really deep like engineering thing that like you wouldn't realize unless you were like me and Jack, you've been like burned by this like many, many times before.
And I think like...
We're at this state now, right, where we've, you know, we've raised another $400 million.
I have to go buy another compute cluster.
Like, you know, like we're going to have like really, really, really large runs and inference and training sets.
And so getting those foundations right is what's actually going to let us do more ambitious things.
And to kind of answer your question, actually, that's a lot of the bottleneck to making biology more like engineering.
It's just like having the right engineering primitives supporting it.
I have an analogous tangent on the model side.
Actually, one of the things that's kind of nice about those problems is they're like super visible.
So like at least you know, like, hey, this crashed, this failed.
For us, we just see like loss curve didn't go down or like we see weird gradient behavior or whatever.
I think...
A lot of these same principles like, you know, engineering first, that also applies on the research team.
One thing that I like to say is kind of like complexity and being bitter lesson pill, they're like fundamentally at odds.
For example, I think like outfold three, I might get this number wrong, but I think it was like 23 submodules.
And at that point, that's a really difficult system to optimize and study.
You're like, all right, what happens if I change, like if I tweak this thing in submodule 30 or like.
21, what happens to the whole system?
And you can always think, hey, we can make this better by adding module 24, but should you?
Or should you think about just removing things and lowering that complexity down?
But I think that's like...
A pretty fundamental thing at CHI is just like the engineering culture and just being like very simplicity biased.
Have you all seen the picture of like the SpaceX engines?
It's like Raptor 1.
It has a bunch of pipes and like Raptor 2.
We have a picture of that like on our office wall because I mean, it's just true, right?
Like how do you delete, delete, delete more things?
Yeah.
But the only way you can accomplish that is...
I mean, the reason AlphaFold 2 and AlphaFold 3 worked, they were small models, relatively speaking.
They were very compute intensive, but they were very data efficient.
Yes.
And like there was inductive bias after inductive bias brought in by human intuition and probably like hard fought experience.
They're incredibly efficient.
If you try to knock down those things, you know, they're not like a house of cards.
Like everything is a...
incremental improvement on top of it.
In order to get beyond that, it seems to me like you really just need new sources of data.
You would need to at least treat data fundamentally different in a way that is much more efficient.
I mean, I mean, I'm actually kind of surprised to hear that you have scale to that degree because it suggests that you're doing something very different from what the community is thinking, the way the community is thinking about it.
I don't know if you can comment about that, but.
We're pretty first principle people like the whole research team at CHI.
uh except for me and kevin really um like we're the only people with quote bio background even still like we're pretty far removed so i think like we we try to like look at every problem as a core ml problem we try to think of like what's the analog in other spaces so like um even for image models like cnn's were built to process images so like images should be looked at and patches like that was the nice inductive bias there then people are like well you can just kind of tokenize this thing throw it into transform and it's going to work and like It did end up working, even on a relatively small data set.
But I think for proteins in particular, it is really hard.
There's not as much structural data.
There's a ton of sequence data, and that's one of the unlocks for ESM working.
You can get that to just run on a transformer.
If you try to do the same thing with experimental structure data, good luck.
You need AlphaFold.
There was that Apple paper where they distilled on the AlphaFold, which it was actually really cool that you could distill on a very large data set, and you could get...
you know good signal but you know it didn't generalize at all because it wasn't reasoning it was really pattern matching yeah like one of the things these like triangle layers you were talking about for example uh they do have a very nice inductive bias maybe it's not the triangle inequality like the paper originally proposed but it's a clean inductive bias and it unambiguously is like one of the the things which made it work and it just comes at a huge cost yeah Yeah, no, I think that's definitely true.
These layers are pretty costly, and that kind of limits what you can do with the architectures.
Not only are they costly in terms of compute, they're just not efficient on modern GPUs either.
You have small hidden dimensions, large sequence dimensions.
It's exactly the opposite of what GPUs are designed to process.
One takeaway from triangle layers is you're kind of just trading off parameters for compute.
in that sense like that's like one mental model for thinking about this uh i might want to like throw more compute at the problem and just trade that off for parameters because i won't be able to hold as many like i can't literally store these you know large pair representations and still do normal attention uh so i think there are fundamental things you can abstract from the ideas like alpha fold um but you can kind of just like tweak these and start building off of them in your own way it sounds like you have quite a bit of research, like fundamental research going into this direction for, I guess, audience looking for a nerd snipe and ML engineering for new problems.
Probably something very, it's a very different research direction than a lot of the communities going in.
Yeah.
Yeah.
I think what we built at Chai is like, it's, it's.
very unique in a lot of ways, but also very tied to like what CoreML is good at.
Kind of what I was saying before, like we try to map every problem into like a CoreML problem.
We think, you know, how would you approach this if it were an LLM or something like that?
But yeah, like at the end of the day, we really, really value simplicity.
And we really encourage people who don't have a bio background to like not be scared of this stuff.
And I think that extends into the product too, where, you know, There's a balance to be had here between how general do you make the product?
Do you build a cross-reactivity workflow and a selectivity workflow and a bispecifics workflow?
Or do you all say, no, let's make the model general enough to say I'm going to condition on arbitrarily binding or avoiding something.
And then you just have a very general screen in your CAD suite where you can say, hey, I just want to avoid or bind to these parts of these different structures.
Kind of like the ML team, I don't have a formal bio background.
Most of the product and platform team doesn't have a formal background either.
Now there's some amount of like maybe regretting my words that I'm going to have, right?
Because I'm sure there are, you know, a million nuances and, you know, I don't want to come off as, you know, too brash or naive there.
But, you know, I think sometimes it's helpful to not be burdened by like all of the, oh, this nuance and this nuance and this nuance.
And you get to kind of bet and be maximally general because, you know, that's kind of what we're seeing in the research.
The models are very general.
That lets the product be very general.
I'm thinking back to like in my CS theory days, my first advisor was like, uh we're working on some problem and we we need like a polynomial time algorithm for something uh and he would always tell me like never underestimate the power of polynomial time like this is basically like you're allowed to choose like whatever exponent you want And my first paper was an end to the 20th time algorithm for this problem.
And I was like, Andy, I did exactly what you said.
He's like, wait a minute.
I didn't mean it like that.
Yeah, but I think you can really help yourself.
You can free yourself up a lot when you're like, all right, I can kind of do whatever I want and then kind of simplify it later.
And I think that's really a pretty fundamental way of thinking about things that we leverage a lot at CHI.
The space of protein design and binders in general is actually a fairly crowded space.
I'm curious about what your general outlook of the field, the industry is.
I mean, I can go back to like some anecdote.
I was at maybe NeurIPS three, four years ago, right?
The one right after RF diffusion came out.
I was talking to someone in the Baker lab and they're like, man, I just one-shotted.
I don't think they even use one shot.
One shot wasn't even a term back then, but they was like, I just got picomolar binders out of RF diffusion and just like threw it in the cryo.
Great, right?
it didn't seem like that just solved the problem like it's not like oh man now every yeah but there are lots of people who i think have seen that you can actually do protein design at least in some categories quite well i'd say like is it many proteins or mini binders um ironically nano binders are actually smaller than or larger than many proteins or maybe like a little bit harder antibodies are typically considered even harder but there's this like Is this something which can and will be commoditized, at least in some part?
How do you compete?
Like, where does this, where do you, where does the field go from here?
I mean, I think the answer is it's kind of all of the above.
Like, I think there probably will be some commodity layer for certain types of modalities or drugs, right?
I think at the same time, we're going to be able to do...
even more and more and more ambitious drugs.
And you're going to, it's just like what's happened in LLM land, right?
Like you have your open source models that are maybe general and helpful for some things, but people are still buying frontier models, right?
And actually, if you look at the amount of value captured, it's actually the closed source frontier models.
You know, the whole pie is growing, but it's growing so fast that even as the open source models like share expands, the frontier models are still able to capture the majority of the value, right?
Raise your hand if you're using an open source model on your day-to-day.
Right.
And what are the reasons for that, right?
One, like if you have, you know, more intelligence, you're going to go after harder tasks, right?
I think if we have more, you know, intelligent bio models, we're going to go after more, more crazy bio tasks, right?
But then also too, like, I mean, a lot of the reason I don't use the open source model is because like, you know, I don't get like cloud code, right?
I don't get like cloud, you know, I think there's like a product layer to be built that is just as important as the model layer.
We learn a lot from our partners and, you know, the people in the building as well.
Just like, what are the really tough things that they get stuck on using the models, right?
And some of them are like, you know, the dumbest things, right?
Like, you know, I want to be able to better visualize this piece and like focus on that.
And some of them are actually like very sophisticated things that we then have to build some like pretty vertical product for.
And look.
Maybe in the fullness of time, like AGI, like one shots everything and doesn't matter.
But I think there's quite a bit of time until we get there.
Right.
And I think the product makes a huge, huge difference for that.
That'd be my answer.
I mean, you probably have a more model forward answer.
No, I think like biology is slow, which is like one kind of nice thing.
And there's like not that much labeled data.
So like you could take all the publicly available sequence information out there.
That might give you a good base model, but you still need some measurements on that data.
That's still pretty time consuming.
And then you need to like iterate on that.
So I think there are even just data blockers there and unlocking like if we really want to do this.
zero-shot design candidate start generating molecules that are almost ready to go into the clinic.
I think there's more to that than just like, you know, AGI might not solve that right away.
I think there are definitely like some technical blockers there.
But even in the space of, you know, specialist companies, I mean, I'm not going to like just start naming them, but there's, I think, I don't know, probably 10, 15 protein design startups.
I think the two things which it sounds like Chai has gone on is like one, all-in-one product, and two, you are not trying to do your own platform.
If you don't have your own data mode, you know, is that going to like help you one out in the end or is that going to be, you know, a blocker?
I don't, I'm just curious about that.
Yeah, that's a great question.
Yeah, so Chai, definitely no plans of like starting a pipeline.
Like we take the partnership model pretty seriously.
Uh, and we, I, Just like from a personal stance, I love the incentive alignment and between like, you know, we make the models better, the partners succeed more and just like, you know, that iterates on itself.
So like, I think that's like a pretty unique part of Chai is like one, just being able to partner with a lot of people to getting like the feedback on the product.
So like, you know, knowing that it's very real, this is in like, like legit big pharma hands and they're actually running campaigns on this stuff.
So I think.
It's interesting.
We really have to be model forward, model focused.
We need to keep delivering value.
So that puts a lot of pressure on the research team, the product team, first of all, to serve these things.
The research teams always shoot for better and better versions.
The way I think about this is if you're a bitter, less impaled forward kind of thinker or company, then there kind of comes a certain point where there's a lot to do on both the model and data side.
But I don't think either is exhausted.
It would be stupid to say, like, we don't need any more data, but it would also be stupid to say, like, the models are stuck.
We only can, like, use data to solve these problems.
So I think there's, like, tons of room to grow on both sides.
We're taking, like, both very seriously.
And I would also maybe push back on the no data moat premise, right?
That'd be kind of like saying, hey, like, all the enterprises that work with Anthropic, like, you're not letting, like, Anthropic train on their data.
So, like, you can't, like...
build models that are good at enterprise workflows, right?
I think, you know, one, we are investing in this, right?
You know, there are ways to turn compute into data and get more and we're doing those, right?
But then also too, okay, what is the kind of data that you're trying to get, right?
And I think what is kind of cool about, you know, working so closely and supporting so many of these partners is we get to really learn about...
you know, what is like the stuff that would be helpful in research, right?
And so rather than doing research in a vacuum, you know, based on what would hypothetically be cool, we're able to sort of kind of do informed research based on like, you know, what our partners have just been very organically asking us for help with.
I see.
Do you, I assume that you are allowed to train general models based upon your partner's data.
Do you?
train specialized models for like, is there an artist model in a Pfizer model?
Yeah, I mean, like a lot of these deals, you know, and this is all public, right?
We are working with them to, you know, train or fine tune a version of our model for them.
And I think there's probably like so much more we can do there over time.
My brother started a company called Applied Compute, a great company.
They're kind of doing this thing for, you know.
design for LLMs, right, and helping enterprises really understand the value of their language data and do that for specialized tasks.
I think there's a whole world where we could potentially do that for biological data.
What is the value there?
Like, what is the lift that you get from using their data?
I mean, is it just that it's more data or is it more that it's specialized to a problem?
You know, they have a lot of like...
scientific, you know, data that they're getting from experiments that can maybe help our models do better in like particular classes of candidates that are targets that they care about.
Yeah.
I mean, even something as simple as like they might just have some preferred way of doing things that might not be like native to the CHI model.
And they can like, you know, kind of like ask the product team and in a sense to just be like, hey, we like, you know, our designs have property X.
Can you make sure that they have those?
So I think like even things as simple as that.
actually have like a pretty big impact for them.
Yeah.
So, I mean, this goes along with a pet hypothesis I have that all AI companies and especially bio and scientific ones are actually consulting companies.
Pharma, I think, is particularly the case because you're developing a new drug, right?
It's almost by definition new, right?
So, like the existing stuff has to be customized in many cases, right?
unless you're doing something that's just reiteration of old stuff.
But a lot of the big pharma are pushing the boundaries of science.
Yeah, I mean, certainly like we aim to make the models very general.
We aim to make the product very general.
We aim to make it powerful.
But yeah, I mean, there is integration work, right, with every customer.
To answer your question, you do get some defensibility just by doing that, right?
And I think what is nice about building, you know, trusted relationships with these partners is hopefully, you know, if we execute really well over the next...
you know, the first year, then they'll continue working with Chai to do more ambitious and more directs past that.
I mean, it's going to be hard to switch, right?
I hope so, yeah.
Just getting the security review done.
Yeah, yeah.
Maybe one other interesting point is like, if you think of this like on a per token basis, I don't know if there's another domain where like the downstream value of a token is like...
as valuable as it is for pharma.
Yeah, that makes sense.
You're thinking about the actual drugs that come out.
These can be multi-billion dollar assets.
In the case of GLP-1s, I think the two GLP-1 drugs combined are maybe a trillion dollar asset.
Yeah, up until I think three months ago, GLP-1's total revenue was more than all of the AI labs put together.
I don't think people realize that.
Like, I didn't realize that.
It's crazy, right?
But you have the market cap way lower.
It's like crazy how, relatively speaking, the market cap is.
And, you know, I didn't realize how much of like a VC business, you know, pharma is in, right?
They're in some sense like taking really ambitious bets.
You know, I think one of the things that was really cool with, you know, is like if you study the history of Silicon Valley, right?
Obviously, people think of Silicon Valley with software, but, you know, in the 80s, one of the biggest venture outcomes, one of the first ones was Genentech, right?
Because it is such a VC model, right?
You get the string of tokens that can then give you so much value downstream.
Just a general shout out to Outposting's blog series about finance and funding.
Yeah, really fantastic.
Before that, I knew a lot of those points, but I did not realize just how deep that rabbit hole went.
Yeah.
Yeah, I mean, it's maybe the single biggest problem in biopharma is actually just the funding model.
There's also, have you heard of Aram's Law?
Yeah.
Oh, yeah.
Yeah.
More backwards.
Yeah, More's Law backwards.
So it's like, and like compute, you know, it's kind of scales.
So you have like this nice exponential scaling, log linear scaling of compute, and you have the exact opposite in pharma.
So like the cost of actually making a drug in pharma is kind of like increasing exponentially.
So the amount of money put in per drug is growing at kind of like an exponential rate, which is, it's pretty interesting to see this, you know.
Which guarantees at some point the marginal return on a new drug development will be negative.
Exactly.
So unless someone, I mean maybe Chai, figures out how to, you know, fix this.
I think that...
We might be on the verge of sort of flipping some of these sections.
Bending the S-curve.
Yeah.
Just to double, maybe belabor the point, but that...
Pharma and VC fundamentally both are optimizing a portfolio.
Yeah.
And I think that's the connection there.
Yeah.
Thinking of pharma as like sophisticated capital allocators, right, where they have this portfolio of targets and they're allocating between them, I think that was a big reframe for me.
Yeah.
And I think we will just see more of that in the future, right?
And hopefully they can take, you know, in a sense of VC taking riskier bets, like hopefully pharma can take riskier bets and pursue really, really cool targets in the future.
that analogy is actually like uh one the the kind of like vc type investor ish model it's like actually how we think a lot about research at chai as well our research team is is relatively small i think definitely compared to like a lot of the like the isomorphic steep minds uh like our research team is like you know in the around 10 people.
So like we're a relatively small team, but we kind of think of it as almost like an investing job where like you're investing ideas towards compute.
In the same sense, you're really just capital allocators in that respect.
Yeah, I actually think maybe this is too cute, but I would even make the broader point, which I think we kind of think of everyone at CHI as a bit of a capital allocator.
So I think one of the things that surprises people is we're pretty small.
We're only 30 people.
And that's because everyone we hire onto the research team or the engineering team.
you know, especially now that they're in some ways like very empowered with AI, a lot of it is just like allocating, you know, their attention into the right ideas and allocating their compute.
This is actually, I think, a characteristic to some extent of machine learning AI projects and also science, right?
Whereas if you're building like an API for some B2B SaaS company that's not building foundation models, whatever, your limit is mostly people.
So the resource you're allocating is almost entirely people.
Whereas if you're building hardware, you're building AI models, you're building something scientific, then your constraint is...
those, the resources that are, you know, the bottleneck is, you know, the lab, it's the compute, it's other things.
And so that you have to really be in that mentality of, I have these limited allocation of, I have some shots on goal.
How do I allocate those shots?
Well, I would say yes and no.
So I agree it's a bit more like that, right?
But like, let's going back to the example of building an API for, you know, a B2B company, right?
That API has incremental cost.
You have to support it.
It adds complexity to the product.
It's another thing you have to go market and sell.
Maybe you should actually be allocating that into like a different...
bet, right?
A different thing on your product roadmap that you should be prioritizing instead of the other thing.
I think in a world where like building things just gets like really cheap and, you know, increasingly free, the scarce thing is the attention both that you can put into it, right?
To keep your product simple and grokkable and that your customer can put into it to like really understand how to use it.
I see it less as like a binary thing and more just like we're all kind of as engineers going to be a little bit more like allocators of attention.
Yeah.
Which is what executives are.
We're all just becoming...
Well, I mean, like, there's a podcast with Satya Nadella, right?
He says, you know, Microsoft wants to make everyone a manager of infinite minds, right?
If you, like, really take that to your extreme, like, everyone's going to be an executive.
I mean, I certainly feel like an executive when I talk to Claude every day, right?
Yeah, yeah.
A little suite of interns who are all going out and eagerly solving problems you may or may not have actually wanted, but they're solving the problems.
Yeah.
So we have two typical questions that we...
asked that we've already kind of asked one, but I'm going to ask it again, maybe more directly, is if you, and you can both answer this, if you could remove a bottleneck from your problem space by fiat, what would that be?
That's an interesting question.
I think one thing that would be really nice, like just, I'm like always in research land, very hard to turn off.
For me, it's probably just the validation loop of protein design in general.
So like just...
being able to say, like, instantly, like, hey, this thing works, this thing doesn't, there's still a bit of walking around in the dark that you're doing.
Just to, like, you know, you have some ways, and, like, I think at CHI we've taken this, like, very seriously, but it's probably along the lines of just, like, validating hypotheses and, like, you know, knowing for certain that things work.
Yeah, that's unsolved problem for sure.
Unsolved problem, yeah.
Yeah, and it would be hugely valuable.
Hugely valuable, yeah.
I'm going to take a much more abstract answer to that, which is actually like talent obscurity.
I think, you know, there's a lot of smart people going and working on LLMs.
You know, there's a lot of people that are working and becoming software engineers for SaaS, right?
But I think just like not that many like smart people go and work on bio.
You know, I didn't work on bio like in high school because I was like, oh, I could like pick up my computer and program apps.
But if I want to work on bio, I have to like go study and get good grades in school and like maybe get a PhD or whatever.
Right.
And, you know, maybe that's one reason for it.
I think another reason is, you know, a lot of this stuff is really obscure.
Right.
Like we threw around a lot of big words during this podcast.
You can't really visualize the things.
It's one of the things we care a lot about at Chai is like, how do we make the whole thing feel visual on our website and in the product?
And, you know, part of the reason we're here is like, you know, I think, you know, more people should realize like you don't need to like have like a super, super, super specialist bio background to contribute to this like computationally.
And so.
You know, I think a lot about like talent flows and like where talent goes in the economy.
And right, you know, in the 90s, everyone was flowing to talent.
And, you know, since the 2000s, people have been flowing to tech.
But, you know, big tech like ate up a lot of the talent, you know, until, you know, a few years ago.
And now maybe like LLMs and the big AI labs are eating up a lot of the good talent.
But it's like, you know, at the meta level, like how do you allocate talent better?
You know, selfishly, I want more talent going into bio.
I mean, we probably want more talent going into manufacturing and physical world things and these other problems that the U.S.
has.
But, yeah, I think communicating that better would be the thing that if I had a megaphone to talk to everyone, I would try to do that.
Okay, so then that leads to the second question, which is, and maybe the answer is the same, but what is the takeaway, one takeaway that you would like people to have from the episode?
Yeah, I mean, I think, you know, biology has been this somewhat obscure feeling field where you're stumbling around in the dark.
You don't know what you're looking at.
You're dealing with non-determinism in your experiments.
You're having to do a very long and iterative trial and error loop across a very, very long amount of time.
at some point you're crossing that threshold of what you can do computationally.
When you can get folding models down to being within, you know, an angstrom, right?
Where you can get design models to give you, you know, hit rates, you know, north of 50%, or now you can put them, you know, in a 96-well plate and actually have like 48 interesting binders.
You start to get to the point where now you can declaratively precision engineer what you want rather than betting on, you know, nature or trial and error to get you there.
And I think that, look, we had the same thing happen in software where you can write code and you can deterministically get an outcome.
Or in electrical engineering where, you know, you, instead of your schematic being drawn out, you can put it in cadence design systems and get it on, you know, it made in software, right?
Or CAD for mechanical engineering where you can sort of precision engineer your part and get it printed or manufactured.
you know, the same thing is happening in bio and it's happening very quickly.
And that really opens the door for a lot of really interesting people, or maybe it wasn't as inscrutable or accessible before, right?
Like software engineers like myself, researchers like Matt, you know, obviously we're still going to want the specialists, but, you know, the generalists can often really accelerate the precision engineering happening in the domain.
Yeah, I think for me, like the base takeaway is that the field is actually working.
Not only does it have commercial traction, but the research is actually showing signs of life.
It's not even just showing signs of life.
The signs of life have been shown.
We're actually in a place where the models work, they're delivering value, and there's still tons of really interesting research problems to solve.
So I think there's a lot more low-hanging fruit in this field than there would be in other fields.
And I think the amount of impact you can have, especially as a researcher, is just unmatched in this field.
For us, we're all very mission-driven.
But even if you're not, It's a lot of fun puzzles to solve.
Like there's like this kind of 3D geometry angle.
There's like, if you like diffusion models, there's like a million problems to solve in that regard.
We have this LLM looking trunk in like Chai 1.
There's just so much of like core machine learning is touched by these problems.
We're still, although we've made a ton of progress, there's still a lot to be done.
And I think it's just like one of the most interesting fields to be working in, which like while also having some of the largest impact on just like humanity.
Cool.
Thank you so much.
Thank you for having us.
Thank you for making a long journey.
Yeah.
22 minute walk.
Yeah.
And, you know, we look forward to tracking Chai's progress.
Awesome.
Thank you guys.
Thank you very much.