4 sources healthy · latest episode 9 Nov 2026
opinion claim

The speaker thinks Lean works very well for narrowly fine-tuned logical reasoning and that using Lean as a verifier could make the approach easy.

Unresolved speaker · ⚡️Math Olympiad gold medalist explains OpenAI and Google DeepMind IMO Gold Performances · 24 Jul 2025

In their words

The transcript segments this claim was taken from

“for the logical thinking and reasoning,”
“I think we can, a lot of people trying to use lean,”
“because like”
“Our AI work super well for very fine-tuned one,”
“and so if we can just use Ling to kind of become the verifier, then it's easy.”
19:23Report a misattribution
0.75how strongly it was put, not whether it is true
0.80importance to the conversation
0.82confidence the claim was read correctly