Sartran: AlphaProof develops an alien style by learning from self-discovered proofs
Laurent Sartran · No Priors Ep. 90 | With Google's DeepMind's AlphaProof Team · Nov 14, 2024 · at 24:57
Google DeepMind AlphaProof researcher Laurent Sartran explains how the formal mathematical reasoning system discovers proofs autonomously.
0:00 / 0:14exact quote · 14.9s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“The way alpha proof currency operates there is that it discovers its own proofs, and when they are valid, it learns from them and develop its own style which has been commented upon as looking, yeah, quite, quite alien.”
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 Laurent Sartran
Sartran: Translating all known human proofs would save years of compute
“With more supervised data, we can avoid the exploration problem, and we could translate all the proofs that are known to man, and that certainly would make the agent much better, and that would save us years of compute for sure.”
Sartran: Human creativity matters more in theory building than theorem proving
“It seems that there is more room for human creativity, human taste human skill in building theories than in the proof part.”