One of Google’s recent Gemini AI models scores worse on safety

A recently released Google AI model scores worse on certain safety tests than its predecessor, according to the company’s internal benchmarking. In a technical report published this week, Google reveals that its Gemini 2.5 Flash model is more likely to generate text that violates its safety guidelines than Gemini 2.0 Flash. On two metrics, “text-to-text […]

  • Related Posts

    Hedra, the app used to make talking baby podcasts, raises $32M from a16z

    Hedra, which offers a video generation and editing suite powered by its Character-3 model, has raised $32M.

    Continue reading
    Harvey reportedly in discussions to raise $250M at $5B valuation

    Harvey AI is in discussions to raise more than $250 million in a funding round led by Kleiner Perkins and Coatue that would value it at $5 billion, Reuters reported

    Continue reading

    Leave a Reply

    Your email address will not be published.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

    You Missed

    Hedra, the app used to make talking baby podcasts, raises $32M from a16z

    • By staff
    • May 15, 2025
    • 1 views

    Harvey reportedly in discussions to raise $250M at $5B valuation

    • By staff
    • May 15, 2025
    • 1 views

    Grok is unpromptedly telling X users about South African ‘white genocide’

    • By staff
    • May 14, 2025
    • 3 views

    OpenAI brings its GPT-4.1 models to ChatGPT

    • By staff
    • May 14, 2025
    • 3 views