Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean — mentioned by ogogmad

Fri, 23 May 2025 10:17:51 GMT

The article also suggests that you could use a proof-verifier like Lean instead. Using that capability to generate synthetic data on which to train helps too. Very large context windows have been known to help with programming, and should help with mathematical reasoning too. None of this gives you AGI, I suppose, but the important thing is it makes LLMs more reliable at mathematics. Anyone have a link to an article exploring Lean plus MCP? EDIT: Here's a recent Arxiv paper: https://arxiv.org/abs/2404.12534v2, the keyword is "neural theorem proving" I've just remembered: AlphaEvolve showed…

Paper and discussion history. A mention is not an endorsement.

Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean — HN submission

Thu, 12 Sep 2024 05:34:47 GMT

Towards Large Language Models as Copilots for Theorem Proving in Lean

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean · HackerPapers discussions

Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean — mentioned by ogogmad

Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean — HN submission