Get your free personalized podcast brief

We scan new podcasts and send you the top 5 insights daily.

Alex Rives expects biology to follow a pretraining-plus-elicitation recipe, but says reinforcement learning must be verified in laboratories. Because biology is empirical, he envisions AI systems proposing real experiments, running them, learning from actual results, and recursively improving their biological models over repeated improvement cycles.

Related Insights

Moving beyond simulation, Genesis uses a cycle where their AI proposes molecules, a pharma partner synthesizes and tests them in a wet lab, and the experimental outcomes are used as feedback to retrain the generative model. This is akin to RLHF but with physical experiments.

Future progress in biology requires moving beyond static models. The new paradigm involves an AI that reasons over hypotheses, prioritizes experiments, learns from the empirical outcomes, and updates its internal world model. This creates a scalable, closed-loop system for scientific discovery.

The "one-time subsidy" of high-quality internet text is largely exhausted. The future of data for training models lies in creating reinforcement learning (RL) "gyms" where agents work on hard, verifiable problems (e.g., coding, math). The environment and the agent's progress become the new data source for recursive self-improvement.

Unlike math or code with cheap, fast rewards, clinically valuable biology problems lack easily verifiable ground truths. This makes it difficult to create the rapid reinforcement learning loops that drive explosive AI progress in other fields.

Applying AI to biology isn't just a big data problem. The training data must be structured for reinforcement learning. This means it must be complete (including negative results) and allow for a feedback loop where AI predictions are tested in the lab, and the results are used to refine the model.

The path to AI self-improvement isn't uniform. It is happening first in software engineering and AI research because these fields have cheap, fast, and verifiable feedback (e.g., unit tests). This capability won't automatically transfer to domains like biology until similar closed-loop systems are built.

Building biologically relevant AI is not a one-off process. It demands a continuous "lab in the loop" system where wet lab experiments generate proprietary data to train models, whose outputs are then physically tested in the lab. This iterative feedback cycle constantly refines the model's predictive accuracy.

Instead of relying on digital proxies like code graders, Periodic Labs uses real-world lab experiments as the ultimate reward function. Nature itself becomes the reinforcement learning environment, ensuring the AI is optimized against physical reality, not flawed simulations.

Current LLMs fail at science because they lack the ability to iterate. True scientific inquiry is a loop: form a hypothesis, conduct an experiment, analyze the result (even if incorrect), and refine. AI needs this same iterative capability with the real world to make genuine discoveries.

The key to creating frontier AI models is no longer just pre-training data or distilling from other models. The real differentiator is building superior interactive environments for reinforcement learning. Labs that create the best environments for specific tasks (e.g., front-end coding) can generate unique improvement loops, leading to state-of-the-art performance.