Topic
10 facts from 1 episode, in date order. These are what speakers said on the shows, each linked to the moment it was said. They aren't independently verified.
2025
Ian Quigley says Anthropic and OpenAI models at that time could not reliably convert SMILES strings into non-canonical SMILES strings.
“none of the Anthropic or or OpenAI models at the time could even convert smiles to non canonical smiles very effectively.”
2026
Ian Quigley says the benchmark separates agents well across different model families and capability levels.
“we get great separation of agents across, uh, model families and different levels, that kind of stuff.”
2026
Ian Quigley says weaker models keep making small variations on molecules that will never work instead of moving on.
“they'll just keep running little subtle changes on molecules that aren't ever gonna go anywhere”
2026
Ian Quigley says medicinal chemists who reviewed the agents' reasoning found it plausible for a structure-activity relationship campaign.
“when we get medicinal chemists to look at it, they're like, Yeah, no, those are very plausible thoughts about, you know, how to conduct this particular part of the SAR campaign.”
2026
Ian Quigley says a new frontier AI model has been released roughly every eleven days.
“there's been a new frontier model drop, what, like, once every eleven days.”
2026
Ian Quigley says DeepSeek V4 Flash performs reasonably well on Leash Bio's benchmark.
“They're, uh, Deepseek V four Flash is pretty good, not that bad.”
2026
Ian Quigley says that around February AI models became able to work with chemistry in a meaningful way, which led Leash Bio to build this environment.
“around February, like a lot of other things, uh, it became clear that they could start to actually work with chemistry in a meaningful way”
2026
Ian Quigley says agent decisions get much worse when information about the molecules is removed, suggesting the agents use it.
“when we remove the information about the molecules, like, these decisions really suffer.”
2026
Ian Quigley says Leash Bio does not use Bayesian hyperparameter optimization as a baseline because he thinks the landscape is too spiky and too high-dimensional.
“We think it's too spiky of a landscape and it's very high dimensional.”
2026
Ian Quigley says it is not yet known whether reinforcement learning progress in these environments transfers to new biology.
“And then we don't yet know if we're able to take reinforcement learning progress from these kinds of environments and move it into new biology yet.”
Episodes