AI-Written Formal Proofs Become a Software Assurance Tool
Agent-generated, machine-checked proofs are lowering the cost of formally verifying production code, so more security-critical software will ship with proof artifacts and human effort will shift to writing and auditing specifications.
weakening · confidence 38 · Emerging (watchlist) · tracking since November 11, 2026 · updated November 12, 2026
Score history
Daily conviction score, 0 to 100. Higher means the thesis is more strongly corroborated.
Now 38 · -2 since Nov 11 · ranged 38 to 40
Why the conviction moved
- Nov 11Strengthened +5
DeepMind's AlphaProof code agents produced Lean proofs that Signal's compiled encryption code meets its specification. They generated millions of lines of machine-checked proof in about four weeks against roughly 26,000 lines of human-written spec, and the checks correctly failed on two reintroduced bugs. This is production, security-critical code getting proof artifacts, with human effort concentrated on the specification, as the thesis predicts.
Source trail
Supporting · November 11, 2026
DeepMind's AlphaProof Code Agents Produce Lean Proofs That Signal's Compiled Encryption Code Meets Its Specification
DeepMind's AlphaProof code agents produced Lean proofs that Signal's compiled encryption code meets its specification. They generated millions of lines of machine-checked proof in about four weeks against roughly 26,000 lines of human-written spec, and the checks correctly failed on two reintroduced bugs. This is production, security-critical code getting proof artifacts, with human effort concentrated on the specification, as the thesis predicts.
Google DeepMind
Unlock full source trail, score history, and daily updates.
Unlock TrendsTownsquare
Argue the thesis in Townsquare.