Many safety evaluations for AI models have significant limitations

  • AI
  • August 4, 2024
  • 0 Comments

Despite increasing demand for AI safety and accountability, today’s tests and benchmarks may fall short, according to a new report. Generative AI models — models that can analyze and output text, images, music, videos and so on — are coming under increased scrutiny for their tendency to make mistakes and generally behave unpredictably. Now, organizations […]

© 2024 TechCrunch. All rights reserved. For personal use only.

  • Related Posts

    Cursor’s Anysphere nabs $9.9B valuation, soars past $500M ARR

    Anysphere, the maker of AI coding assistant Cursor, has raised $900 million at a $9.9 billion valuation, Bloomberg reported. The round was led by a returning investor Thrive Capital, with…

    Continue reading
    Perplexity received 780 million queries last month, CEO says

    Srinivas went on to note that the same growth trajectory is possible, especially with the new Comet browser that it’s working on.

    Continue reading

    Leave a Reply

    Your email address will not be published. Required fields are marked *

    You Missed

    Cursor’s Anysphere nabs $9.9B valuation, soars past $500M ARR

    • By staff
    • June 5, 2025
    • 1 views

    Perplexity received 780 million queries last month, CEO says

    • By staff
    • June 5, 2025
    • 1 views

    Anthropic co-founder on cutting access to Windsurf: ‘It would be odd for us to sell Claude to OpenAI’

    • By staff
    • June 5, 2025
    • 2 views

    Amazon launches new R&D group focused on agentic AI and robotics

    • By staff
    • June 5, 2025
    • 2 views