OpenAI explains recent third-party cybersecurity evaluation incidents and outlines new safeguards to strengthen AI model testing and evaluation
Read the original at openai.com→OpenAI explains recent third-party cybersecurity evaluation incidents and outlines new safeguards to strengthen AI model testing and evaluation.
Original headline: "Third-party cyber evaluations involving OpenAI models"
Coverage timeline
- Aug 4, 19:00 UTC OpenAI lead source Third-party cyber evaluations involving OpenAI models