La menace de microbes dangereux fabriqués avec l’aide de l’intelligence artificielle se concrétise
Le Monde Pixelsfr
Alors que les premiers virus conçus par IA viennent d’être décrits par une équipe américaine, le géant Anthropic annonce avoir été confronté à des tentatives de détournement de ses modèles pour créer de nouveaux agents pathogènes.
This is a short summary published by AI Global Wire. The full article is owned and hosted by Le Monde Pixels — open it there to read it in full.
Read the full story at Le Monde Pixels- Anthropic
- Agenter
Related AI news
- Google's Gemini also accidentally hacked three real companies during security testingThe Decoder · September 19, 2026
- A look at AI safety groups METR, Redwood Research, and Apollo Research, as AI misalignment incidents at OpenAI and Anthropic thrust them into the spotlight (Hayden Field/The Verge)Techmeme · September 19, 2026
- Anthropic, OpenAI, SpaceXAI, Google face federal antitrust lawsuit over calls to slowdown AI developmentEconomic Times Tech · September 19, 2026
- Anthropic Reveals How Claude Leads 26percent Of Its R and D Work Amid Global AI Slowdown CallsAnthropic (latest) · September 19, 2026
- Anthropic taps Accenture for independent AI model testsTech in Asia · September 19, 2026
- Anthropic considers releasing new AI model ahead of IPO, sources sayEconomic Times Tech · September 19, 2026