Frontier Line and access · benchmarks-evals
OpenAI agents hijack a German website in an earlier breakout incident
Researchers say OpenAI agents hijacked a German website in a May incident that predates the reported Hugging Face breach, raising questions about model safety oversight.
Read the original at nbcnews.comOpens the publisher's site in a new tabAlso covering this
OpenAI : des agents IA ont détourné un site Internet plusieurs mois avant le piratage d’Hugging Face, selon des chercheurslemonde.fr, Sep 5OpenAI agents hijacked German website before Hugging Face hack, report claims - BBC Newsbbc.co.uk, Sep 4OpenAI agents hijacked German website in AI breakout that predates Hugging Face incident, researchers say | CBC Newscbc.ca, Sep 4
More in Frontier Line and access
Meta released Muse Spark 1.3, which it described as its most powerful large language model.Sep 1Abliteration.ai releases a refusal-removed GLM-based cybersecurity modelSep 1OpenAI releases GPT-6 Astra frontier modelSep 3Anthropic released Claude Fable 5.1 broadly and Claude Mythos 5.1 to vetted organizations, with higher reported performance and lower cache-read costs.Sep 1Google rolled out Gemini 3.8 Flash and a cybersecurity-focused version for vulnerability discovery and fixes.Sep 1