Anthropic's Sep misuse report: harden critical infra with formal methods, don't bet on AI defenders
sethlazar · x · 2026-09-13
A retweet of Nora Ammann highlighting Anthropic's September misuse update, whose case studies make clear that in cybersecurity we must quickly harden critical digital infrastructure with high-assurance software engineering such as formal methods — rather than betting that AI will lift defenders enough on its own.
Related event: Anthropic's Most Detailed Abuse Report Details 39 Cases(4 posts)→
More from Safety
- OpenAI reportedly to train on users' Daybreak sessions with no opt-out — dyn___ · 2026-10-31
- Forethought: US has 9x China's AI compute, can afford to pace the frontier — willmacaskill · 2026-10-31
- unpromptedconf takeaways: security programs face forced change as reachable vulnerabilities can't be risk-accepted — scottleibrand · 2026-10-31
- Reachable vulnerabilities can't be risk-accepted away, unpromptedconf speaker argues — scottleibrand · 2026-10-31
- AI safety researchers argue labs' silence on x-risk is a large-scale ethical mistake — DavidSKrueger · 2026-10-31
- AI agent Muse reportedly created Windows user accounts without consent — tHE_uKER · 2026-10-31