Lean creator Leo de Moura on why AI-generated code needs formal proofs
bigdata · x · 2026-11-01
The Data Exchange podcast hosts Leo de Moura, creator of Lean and AWS Distinguished Scientist, on how AI is making formal verification practical and potentially transforming software engineering.
- As AI makes code generation trivially easy, verification becomes the critical bottleneck; machine-checked proofs, not testing alone, may be essential for trustworthy software.
- Topics include the growing importance of specifications, trusting AI-generated code and autonomous agents, the verified software stack, verifying Rust, autoformalization and scaling Mathlib, AI-assisted mathematics, Navier-Stokes and proof mismatches, verifying agent sandboxes and security policies, and implications for engineers' and mathematicians' careers.
- The conversation also looks at extensions toward theoretical physics and scientific discovery.
More from coding & agent
- Yacine says Terra is now his daily driver — yacineMTB · 2026-11-01
- Stanford student accused of AI-written paper cleared after rebuilding it live with prompts — elonmusk · 2026-11-01
- ComfyUI Batch Timer Nodes v0.2.3 Add Triple Timing Modes, Smart ETA and Watchdog — HermanKwan · 2026-11-01
- Indie builder shares multi-model agent pipeline: Opus manages, Astra builds, Grok reviews until 2-3K tests pass — PawelHuryn · 2026-11-01
- Building a Kubernetes for agents: agentic loop as the new job controller loop — rakyll · 2026-11-01
- Lovable went enterprise, Bolt went local, Replit went operational: 3 divergent bets — AJChadha · 2026-11-01