Using LLMs for High-Assurance Crypto: A Lean Formal Verification Experiment
jedisct1 · x · 2026-10-22
Cryptography researcher mrosenberg recounts using LLMs on the Kopis key encapsulation scheme: routine AI optimizations left code 2–8x slower than rivals, and riskier optimizations (NTTs, vectorized multiplication, multi-lane hashing) were hard to review safely. The team's answer: add a formally verified Lean implementation, made feasible by LLMs recently getting good at writing Lean—strengthening the paper while guaranteeing correctness of aggressive optimizations.
More from coding & agent
- How a second Mac mini lets AI agents auto-distribute compute-heavy tasks — tedddyoweh · 2026-10-22
- LangChain's Design Agent Shipped 3,000+ Assets and Earned 4.5M Views Since August — LangChain · 2026-10-22
- Databricks Chief AI Scientist: Evals Are the Biggest Bottleneck to Enterprise AI Adoption — jefrankle · 2026-10-22
- Developer plans a solar-aware job scheduler so his homelab rides free excess power — mertdumenci · 2026-10-22
- How do you design your agentic code review workflow? — lucasmeijer · 2026-10-22
- Langfuse now supports custom System One decision models including SubQ Snap — ryanallred · 2026-10-22