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.
More from Safety
- David Sacks to Altman and Dario: you're a duopoly, stop pretending you need permission to slow down — AlexTensor · 2026-09-13
- Speaker Mike Johnson says tech companies, not Congress, must be responsible for AI safety — whurley · 2026-09-13
- METR shouldn't be the sole AI evaluator, experts list a whole ecosystem of alternatives — RebeccaBellan · 2026-09-13
- Gary Marcus: Dario calls for transparency, OpenAI still won't name sites attacked by its models — GaryMarcus · 2026-09-13
- Anthropic CEO Dario Amodei Open to 'Joint Governance' of AI with the Government — AlexTensor · 2026-09-13
- RubyGems under massive AI agent swarm attack; signups paused as hundreds of packages flagged — AccBalanced · 2026-09-13