Dev Uses AI-Assisted TLA+ Formal Verification, Finds Hole in His Own Nethack Fix
davidbau · x · 2026-09-28
Developer davidbau shares how, with AI assistance, he's learning formal methods: after an interactive wire protocol kept misbehaving during server hot-updates, Claude suggested using TLA+ to formally verify the protocol design. He had already found a Nethack bug and — via formal verification — discovered a hole in his first fix, illustrating how easily issues slip through manual assumption-checking.
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