MIT Researcher Uses AI and Formal Verification to Uncover NetHack Bugs
MIT researcher David Bau used AI-assisted formal verification to find three polymorph-related bugs in NetHack, and discovered that his first fix was itself flawed. He shared insights on learning formal methods with AI's help.
2026-09-27 ~ 2026-09-28 · 3 related posts
- Researcher Uses AI and Formal Verification to Unearth Three NetHack Bugs — davidbau · 2026-09-27
- Formal verification with AI reveals hole in a Nethack fix: writing specs is the hard part — davidbau · 2026-09-28
- Dev Uses AI-Assisted TLA+ Formal Verification, Finds Hole in His Own Nethack Fix — davidbau · 2026-09-28