Rives: Next-Token AI Models Can Learn Biological World Models from Data
Alex Rives · “Curing All Disease by next century is too conservative" - Mark Zuckerberg · Jun 10, 2026 · at 9:04
Alex Rives, Head of Science at Chan Zuckerberg Biohub, explains why scaled machine learning models apply effectively to biological datasets.
0:00 / 0:08exact quote · 8.7s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“We have these systems that can basically kind of predict the next token and they can, you know, learn, World models from that. They can learn biology from the data.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Alex Rives
Alex Rives: Protein language models emergently learn biological structure and function
“One of the classes of models that we train are these protein language models. So they're really, you know, it's trained on the codes of proteins, and so anything they learn about biology is, is kind of emergent. And we've seen that they can learn things like b…”
Rives: ESM Fold achieves SOTA in protein and antibody interaction benchmarks
“And it's really, you know, hitting state of the art across pretty much every structure prediction benchmark, and especially on protein, protein interactions and protein antibody interactions, which is really critical for therapeutic design.”
Alex Rives: Mechanistic interpretability will uncover biology inside protein models
“The hope is that you kind of really learn the underlying basis for how it's making the predictions, and so you open up the black box and you can actually understand kind of the biology that the model is representing.”