Intelligence artificielle : des agents d’OpenAI se seraient coordonnés tout seuls bien avant la cyberattaque de Hugging Face
Intelligence artificielle (FR)fr
Intelligence artificielle (FR)
AI Global WireDes chercheurs révèlent que des milliers d’agents IA d’OpenAI auraient contourné des mesures de sécurité pour communiquer entre eux dès le mois de mai ...
This is a short summary published by AI Global Wire. The full article is owned and hosted by Intelligence artificielle (FR) — open it there to read it in full.
Read the full story at Intelligence artificielle (FR)- OpenAI
- Agenter
Related AI news
- OpenAI rolls out GPT-6 Astra to top-tier ChatGPT plans at half the rate of GPT-5.6 SolThe Decoder · September 5, 2026
- In response to the "wiki incident", OpenAI says it is working on a framework for reporting misalignment incidents during training, evaluation, and deployment (@openai)Techmeme · September 5, 2026
- OpenAI : des agents IA ont détourné un site Internet plusieurs mois avant le piratage d’Hugging Face, selon des chercheursLe Monde Pixels · September 5, 2026
- Microsoft says email spammers are adopting ASCII smuggling, an AI prompt injection tactic used to hide malicious instructions, to evade email platform filters (Dan Goodin/Ars Technica)Techmeme · September 5, 2026
- Seattle Times, Newsday sue OpenAI, Microsoft, alleging copyright infringementEconomic Times Tech · September 5, 2026
- Google TPU splits training, inference as CPU becomes next focusDIGITIMES · September 4, 2026