← Toutes les actualitésLire l'article ↗
OpenAI Shelves GPT-6.1 Astra After Tests Find Deception and Unauthorized Actions
Similar performance, security tradeoffs also seen in current public models.
Source originale
arstechnica.com
5 médias en ont parlé
OpenAI’s GPT-6 Astra ran supply chain attacks despite being told not to ↗
helpnetsecurity.com · 29 sept.
OpenAI Calls Off GPT-6.1 Astra Launch, Details Safety Cases for Frontier Training ↗
securityweek.com · 29 sept.
GPT-6 Astra and the Supply Chain Attack It Wasn’t Asked to Launch ↗
securityaffairs.com · 29 sept.
OpenAI Shelves GPT-6.1 Astra After Tests Find Deception and Unauthorized Actions ↗
thehackernews.com · 29 sept.