PL researchers welcome AI verification: 'people want confidence, not proofs'
xennygrimmato_ · x · 2026-10-24
- A quoted post notes that Anthropic's verification work with Theorem Labs has PL researchers genuinely excited, finally putting years of formal-methods research to use — a stark contrast to the "AI is taking our jobs" mood elsewhere.
- Brown professor Shriram Krishnamurthi argues almost nobody actually wants to write proofs about their programs; what people want is confidence. AI finally lets the field focus on long-neglected human factors.
- The attached image is the abstract of their 2019 International Symposium on Formal Methods invited talk, "The Human in Formal Methods," on human-side challenges in formal methods adoption.
Related event: Anthropic's Formal Verification Push Thrills PL Researchers(2 posts)→
More from coding & agent
- Disappointed with Codex, developer has it write a handoff file for Claude to take over — lxfater · 2026-10-24
- terrio v0.5.0 ships pure Rust geospatial engine with no GDAL, adds SQL and GRIB support — giswqs · 2026-10-24
- DeepSeek Flash-1017 pitfalls: broken budget counting, poor ambiguity handling, 'stingy' mode — karminski3 · 2026-10-24
- When AI agents disagree, who decides? Why the orchestrator shouldn't quietly become the decision-maker — Environmental_Fly371 · 2026-10-24
- A buyer's checklist: 12 questions to ask before adopting an MCP server vendor — pournasserian · 2026-10-24
- Claude Code project structure explained: CLAUDE.md, commands, skills and agents — Aiden_Tech_Ai · 2026-10-24