Machine Learning Street Talk · Wednesday, September 2, 2026
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.
“You wrote a very famous paper, which was acquisition of chess knowledge in Alpha Zero. That's right.”
“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.”
“So these could be almost a gold mine for us to dig for new science. Yes.”
“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.”