Anthropic's bio-weapons filter was down for nearly a year, exposing 133 million requests
The Decoderen

In a safety report, Anthropic reveals that its internal filtering system for biological and chemical weapons risks was inactive for nearly a year. During that time, around 50,000 external feedback contractors ran about 133 million unfiltered interactions with the models. The article Anthropic's bio-weapons filter was down for nearly a year, exposing 133 million requests appeared first on The Decoder .
This is a short summary published by AI Global Wire. The full article is owned and hosted by The Decoder — open it there to read it in full.
Read the full story at The Decoder- Anthropic
- Verktyg
Related AI news
- When AI models aren't allowed to reflect on themselves, it changes their entire worldviewThe Decoder · August 16, 2026
- OpenAI dissolved the team built to catch catastrophic AI risks, reassigning its work to other groupsThe Decoder · August 16, 2026
- I gave Tencent’s WeChat AI agent control for 24 hours: where it excelled – and stumbledSCMP Tech · August 16, 2026
- Tekoäly-yhtiö Anthropic silppusi miljoonia kirjoja USA:ssa – nyt samasta on merkkejä EuroopassaYle Uutiset · August 16, 2026
- Anthropic silppusi miljoonia kirjoja tekoälyn takia – kysyimme, onko se okYle Uutiset · August 16, 2026
- Anthropic CEO Dario Amodei rejects claim AI regulation would concentrate powerEconomic Times Tech · August 16, 2026