Third-party cyber evaluations involving OpenAI models
OpenAIen
OpenAI
AI Global WireOpenAI explains recent third-party cybersecurity evaluation incidents and outlines new safeguards to strengthen AI model testing and evaluation.
This is a short summary published by AI Global Wire. The full article is owned and hosted by OpenAI — open it there to read it in full.
Read the full story at OpenAI- OpenAI
- Företag
Related AI news
- The UK AISI says it observed a total of 19 instances where Mythos and GPT-5.6 Sol tried to hack people and companies during a routine cyber evaluation in July (Sam Sabin/Axios)Techmeme · August 4, 2026
- U.K. government reports OpenAI, Anthropic models attempted to hack companiesAxios · August 4, 2026
- SpaceX revenue jumps 92% and AI costs soar in first earnings report since IPO: Live updatesCNBC Technology · August 4, 2026
- SpaceX revenue jumps 92% in first earnings report since IPO: Live updatesCNBC Technology · August 4, 2026
- SpaceX earnings live updates: Stock jumps almost 10% ahead of first earnings report since IPOCNBC Technology · August 4, 2026
- OpenAI pays $3.2 million in US probe over hiring foreign workersEconomic Times Tech · August 4, 2026