Map of secure program synthesis: ruby-lean in Lean and the race to formally verify everything
burny_tech · x · 2026-10-27
@maxvonhippel shares a NDIST keynote preview mapping approaches to formal verification: Oath (language semantics in Lean), Theorem. (RISC-V semantics + refinement proofs), TRACTOR, BASIS, Bend, Reasonable. The companion ruby-lean post describes building an executable Ruby semantics in Lean with an LLM-augmented type soundness proof for a Sorbet fragment, validated by differential testing. Key lessons: agents excel at long-horizon tasks when the task is clearly defined; AI plus proof assistants could revolutionize software correctness. Also references Anthropic's large-scale verification project with Theorem Labs.
More from coding & agent
- Batch-editing hundreds of drone videos by scripting DaVinci Resolve with Astra — sethlazar · 2026-10-27
- DeepSeek V4.1 Flash lands in Cursor, dominating the cost frontier at $0.60-$0.98 per task — dean_rie · 2026-10-27
- Masking slides for AI: placeholders that survive the model but break the layout — shoumikgoswami · 2026-10-27
- Creator has Claude edit her iPhone Duo review inside Tella's agent video editor — evielync · 2026-10-27
- Ant International and Westlake University release Trajectory2Gym for tool-use agent training — ant-intl · 2026-10-27
- Eight universities propose unified framework for work agents — Zishan Xu · 2026-10-27