# The Sequence explains how AlphaProof and DeepSeekMath-V2 use proof checking for recursive improvement

> Original title: The Sequence Knowledge - Issue #968: Learning RSI: Mathematics as a Laboratory for Recursive Improvement

- Source: The Sequence
- Published: 2026-11-10T12:05:44.000Z
- Bad Influence: https://badinfluence.news/items/qt4qtxgftek1y8qz0rc97iy1s
- Original: https://thesequence.substack.com/p/the-sequence-knowledge-issue-968

## Summary

The Sequence examines how AlphaProof, Goedel-Prover-V2, and DeepSeekMath-V2 use a generator and a checker to decide which proofs become training material. It describes how Lean's kernel makes checking easier than finding proofs, and how AlphaProof turns exploration into training, including test-time reinforcement learning. The piece also notes that a checker cannot confirm whether a stated theorem is the one intended.