Topic: ai model safety tests

Sort by: Relevance | Date
  • OpenAI to Share More AI Safety Test Results Regularly
    May 14, 2025
    90%

    OpenAI to Share More AI Safety Test Results Regularly

    OpenAI launched a Safety Evaluations Hub to regularly publish detailed safety evaluation results for its AI models, covering harmful content, jailbreak attempts, and factual accuracy. The initiative aims to improve transparency and industry-wide understanding of AI safety...

    Read More »

Related Topics

Transparency in AI (1) gpt-4o rollback (1) openai safety evaluations hub (1) harmful content metrics (1) jailbreak attempts (1) factual accuracy (1) criticism openai safety protocols (1) opt- testing phases (1)