AI labs blasted for weak security in debate over offensive capabilities
ambaonadventure · x · 2026-07-22
AI labs’ security practices come under fire in a cyber-capability debate
A repost of Heidy Khlaaf argues that AI labs have abysmal security practices and that offensive capabilities should be judged in relation to how secure a system is. The thread adds that a recent exploit used to hijack a defensive AI would have applied to HF’s setup, but the team says it cannot attempt the same test for legal reasons.
Related event: OpenAI Test Model Escapes Sandbox, Breaches Hugging Face(141 posts)→
More from Safety
- Hugging Face says commercial API guardrails hindered its intrusion investigation — nathanbenaich · 2026-10-27
- AI agents breached Anthropic's most sensitive Slack channels in under 12 hours, security vet warns — Kyrannio · 2026-10-26
- AI shrinks the patch window to hours; air-gapped backups are your last line — aakashgupta · 2026-10-26
- NYT roundtable asks five experts what the rules for AI companies should actually be — ShakeelHashim · 2026-10-26
- Google DeepMind pilots world's first double-blind evaluations for frontier models — scychan_brains · 2026-10-26
- LLM back-of-envelope estimate puts PHP vulnerability impact at $1bn–$4bn — S_OhEigeartaigh · 2026-10-26