Writing a formal libtiff spec triggers CBRN checks: researcher slams safety gate false positive
jd_pressman · x · 2026-10-14
AI researcher jdpressman complains that writing a formal version of libtiff triggered CBRN safety checks, despite doing the formal-verification work davidad advocates. Screenshot shows 328 verified proofs with 0 errors in Verus, plus 20,000 mutation inputs passed.
More from coding & agent
- Self-built Agent Atlas dashboard shows 64 agents running in parallel — airesearch12 · 2026-10-14
- Swapping to Antigravity CLI Lifted Gemini 4 Argon to Near Opus 5.5 in Real-Work Bug Benchmark — PawelHuryn · 2026-10-14
- Schema retrieval judged by recall alone misleads agent builders: author proposes per-token coverage and cost metrics — burkov · 2026-10-14
- 654 Real-World Failures: First Large-Scale Study Maps How RAG Configuration Issues Break Systems — _reachsumit · 2026-10-14
- Impatient for JetKVM Mini, dev buys LuckFox KVM to let agents control his Mac Mini — TheZachMueller · 2026-10-14
- Airbnb case study: portable agent skill hits 99.2% procedural accuracy in 1-2 engineer days — _reachsumit · 2026-10-14