The Ledger
Every statement that passed quotation and attribution checks. Mix any filter with any other: certainty 1/5, debate potential 5/5, or both at once.
why aren't all 13 resolved? a statement only gets an assessment when the public record can support or contradict it. opinions and what-ifs never can, and 0 checkable ones are still open, waiting for their date. predictions held up or didn't; assertions are supported or contradicted. on every card: ▮▮▮▮▮ certainty · ▮▮▮▮▮ debate potential. speakers are clickable
Dent: Chai-2 hits nearly 20% wet-lab antibody binding success
“We have about a two week validation cycle in the lab, and two weeks later, we see that roughly close to 20% of these antibodies actually bind their targets in the intended way.”
Meier: Chai-2 maintains success rate on targets with 25% sequence similarity
“We actually even have a slide in our paper in the supplement where we actually look at an even harder subset. So not looking at things that are, you know, up to a sequence similarity with the model, but actually pushing all the way down to 25%. So really looki…”
Dent: Models will generate entire drug candidates in just 20 attempts
“The fact that we can get antibody hits in just 20 attempts, there's no reason that, that we couldn't generate intra drug candidates in that same number of attempts.”
Dent: Chai's models achieve structure error below width of one atom
“They reason quite literally by placing individual atoms in, in three D space. And often they're getting the resolution of these structures, the error down to less than the width of one atom. When we look at the error across the entire structure.”
Dent: Chai generated cross-species binding antibodies testing only 14 sequences
“We ordered actually only 14 sequences to the lab. And I think four of those were histohumans. One of those was a hit to the Sino. One of them was actually overlapped and hit both. That one now allows us to move forward with that program and gives us a whole am…”
Dent: Chai achieved 70% success rate on mini protein binder designs
“I think if you see our mini protein results, we are, I think, close to 70% on those with picomolar affinities, like really, really tight binders for every single target that we tested. So all five targets we tested worked, and 70% of the designs that we ordere…”
Meier: Previous AI bio startups had overly tight lab integration
“Almost every AI bio company before us has had some kind of very tight lab integration with what they are doing. And it almost too tight.”
Dent: Scaling software teams stall without a dedicated architectural steward
“I think you just learn that unless somebody is really taking care to keep the entire system in their head and is an effective technical steward of the architecture, that things just evolve and the sort of the entropy of the software takes over and slows down y…”
Dent: Structure prediction is biotech's ImageNet moment, molecular design is Midjourney
“One piece of intuition around that is that you can almost think about structure prediction as The ImageNet moment for the field, where with structure prediction, we are asking a model to go from sequence to a predicted structure, and it's sort of like a classi…”
Meier: Chai-2 achieved a 50% success rate on tested targets
“The model is not perfect. You know, it worked in 50% of the targets that we tried. Maybe it would have been more, right, for the caveats we talked about before, but, you know, it worked in 50% of cases.”
Chai filtered benchmark targets to under 70% identity from training data
“So we actually wrote a scraper that would go and see what was in stock. We would go and pick out the protein. We would go look at what that protein sequence was. Now we need to make sure this is held out from training as well. Right? So we would take that, tha…”
Dent: Chai Discovery originally targeted only a 1% antibody success rate
“We were actually only targeting a success rate of one percent. That was the company-wide goal for the entire year.”
Dent: Chai spent tens of thousands bisecting Git history for one bug
“We've literally had to do this in Chai's history, but we've had to go and bisect Git history. Run launch training runs, you know, with a sort of a binary search to identify a small enough range of pull requests to identify a bug, then go to that, that, that pu…”