Research #Google Nov 11, 2026 · Originally published Nov 10

DeepMind introduces AlphaProof Code: agents generate over six million lines of Lean to formally verify Signal's protocol implementation in four weeks

Formal verification has been too costly for all but a few critical systems. How DeepMind had agents write the proofs while humans reviewed about 1% of the work.

Primary source Google DeepMind blog · deepmind.google Read the original ↗

// Key points

  • AlphaProof Code is a multi-LLM agentic framework: researchers work with models to turn Signal's security goals into formal specifications, each reviewed by a human expert, and agents then prove autonomously that the implementation meets them.
  • The agents generated over six million lines of Lean and audited their own proofs, flagging about 1% of the codebase for human review; Lean checks the rest automatically.
  • The proofs cover the compiled code that runs on devices, not just the protocol design; the process took four weeks, work DeepMind says historically takes expert teams years.
  • To check it can tell good code from bad, the team reintroduced two real, previously fixed bugs into an isolated copy, and both times the system produced a machine-checked proof that the buggy version was insecure.

Builder's takeFor most product teams this is not a tool for tomorrow, but the split of humans writing specs, agents writing proofs and a machine checking them is worth learning now. I would try having a coding agent write Lean or property tests for a small, high-stakes module like auth or billing, with humans reviewing only the spec. Read with Microsoft's PDD-Kit on 11-06, agents are lowering the bar for formal verification.

// Background · from #Google

Full timeline →
  1. Nov 11 Gemini 4 Carbon opens to all developers at Argon's introductory price of $2 input and $10 output per million tokens
  2. Nov 11 DeepMind releases Gemini Robotics 2.5: 30% to 100% higher success across 200 tasks, and 96% success picking parts on Mercedes-Benz lines
  3. Nov 10 Google adds TPU 8tx for confidential inference and TPU 8i Max, which packages two 8i chips to double compute, SRAM and HBM bandwidth

Every Monday, the week in AI in one email

Every Monday morning: the 6 AI stories that mattered most in the past seven days, with my take, in your inbox.

Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link. See the latest issue →