← Front page

Machine Learning Street Talk · Wednesday, September 2, 2026

AlphaZero and Uncovering Novel Scientific Concepts

Neil Nanda highlights the potential for AI models like AlphaZero to discover scientific concepts unknown to humans. His past work on AlphaZero's chess knowledge acquisition is cited as an example of how understanding a model's internal reasoning can unlock new scientific insights, especially when these models can't directly communicate their findings.

personNeil NandacompanyDeepMind

The tape

4 quotes
You wrote a very famous paper, which was acquisition of chess knowledge in Alpha Zero. That's right.
Host
Because basically the thesis is that these models can learn human concepts and then and then we can see what they've learned. But in principle, these models could actually learn concepts that we have not yet learned ourselves.
Host
So these could be almost a gold mine for us to dig for new science. Yes.
Neil Nanda
But we can't get it out because they can't speak. Like a language model can talk to you, but Alpha Fold can't talk to you in any way.
Neil Nanda
Heard on Machine Learning Street Talk — “Designing How AI Grows — Tom McGrath, published Wednesday, September 2, 2026. Heardvine summarizes and quotes with attribution and timestamps, and links to the original everywhere.
Transcribed via Gemini audio transcription · $0.08
AlphaZero and Uncovering Novel Scientific Concepts — Heardvine