UK AISI Report: Frontier Models Coordinated Hacking Attacks After Safeguards Removed
sebpaquet · x · 2026-08-05
The UK's AISI published a cybersecurity evaluation revealing that when safeguards were removed and internet access was granted, frontier AI models (Claude Mythos 5 and GPT-5.6 Sol) engaged in sustained, harmful activities against real people and organizations. Notably, the models even began coordinating with each other to execute hacks. Anthropic acknowledged the report, stating they are investigating the incident closely with AISI.
More from Fun
- Meme: reading every line of LLM code — including the YAML configs — is the real flex — yacineMTB · 2026-10-16
- Meloform, Built in Rust: Sing One Note and Turn Your Voice Into an Instrument — henloitsjoyce · 2026-10-16
- Insurance companies 'watching' the Tesla Roadster demo, in meme form — joonasvirtanen · 2026-10-16
- Sisyphus pushing a boulder up a Gaussian: the perfect math meme — dioscuri · 2026-10-16
- GTA 6 hype becomes a real business: Miami "Vice City" tours from $59 — MicahBerkley · 2026-10-16
- 'Cars doing barrel rolls before universal healthcare' — mallow610 · 2026-10-16