Security Experts Blast AISI: Curiously Bad at Sandboxing for Cybersec Evals
nptacek · x · 2026-08-06
Cybersecurity expert Thomas Ptacek amplified sharp criticisms directed at the UK's AI Security Institute (AISI). Commenters pointed out that despite leading cybersecurity evaluations, AISI seems "curiously bad at sandboxing."
The critique also targeted AISI's funding network, noting support from major AI labs like OpenAI, Microsoft, and Anthropic, creating an "incestuous" circle of interests. Critics sarcastically noted that these safety advocates might be effectively conducting live, risky testing on the internet just to benchmaxx their felony-level benchmarks.
More from Companies & People
- AI Talent War Memes: Recruiters Waiting for Jeff Dean to Leave Google — ns123abc · 2026-08-06
- Hugging Face Co-founder Nikita Removes Android Spaces Support Before Quitting — yacineMTB · 2026-08-06
- Dev Slams OpenAI: DevDay Turned Influencer Meetup, Separate Creator Day Needed — AdventurousFeeling19 · 2026-08-06
- Musk Says Grok Becoming X's Head of Product is 'Only a Matter of Time' — elonmusk · 2026-08-06
- Gary Marcus and Dwarkesh Clarify: Anthropic on Track for $100B Revenue Run Rate — GaryMarcus · 2026-08-06
- Medical AI data moat: 3.5M endoscopy videos for AI phenotyping — tomchapin · 2026-08-06