Formal verification with AI reveals hole in a Nethack fix: writing specs is the hard part
davidbau · x · 2026-09-28
Researcher davidbau describes using AI assistance to learn formal methods: after finding a bug in Nethack, formal verification exposed a hole in his first fix. His takeaway: spec-writing is itself highly AI-driven — once you can truly say what you want, the proof becomes a triviality on top. He admits it's easy to miss issues while checking assumptions and asks the community for advice.
Related event: MIT Researcher Uses AI and Formal Verification to Uncover NetHack Bugs(3 posts)→
More from coding & agent
- Personal agents from big labs vs one shared company agent: which design wins? — AshishKulkarni1411 · 2026-11-16
- WebArena-Pro launches: 300-task multimodal web-agent benchmark across 20 apps — xhluca · 2026-11-16
- Self-improving agent papers this week: agents learn the benchmark, not the task — TheTuringPost · 2026-11-16
- 1,000 agents, one week, 630k lines: HF builds a weights-free Python chatbot — _lewtun · 2026-11-16
- One-person content agency targets $30K/mo with 11 AI agents — full playbook — VibeMarketer_ · 2026-11-16
- Hugging Face releases definitive fine-tuning guide for 3D generation model TRELLIS.2 — ariG23498 · 2026-11-16