AI Security

    OpenAI's GPT-6.1 Terra is safer overall, but shows more destructive-action flags in tests

    OpenAI reports stronger overall safety alongside more destructive-action flags in testing.

    OpenAI confirmed GPT-6.1 Terra is safer overall than some of its older models, but its safety testing also found other problems.

    B

    BleepingComputer

    Source

    BleepingComputer
    OpenAI's GPT-6.1 Terra is safer overall, but shows more destructive-action flags in tests
    AI Analysis

    Generated insight by OnAirToday AI

    The results suggest that model safety can improve in some areas while risks remain in others. Testing for destructive actions can help reveal tradeoffs that a broad safety label may miss.

    Powered by AI • Not a substitute for human analysisMore Insights →
    Read the full story at BleepingComputer →
    Comments
    Share
    Filed under:AI Security
    #Openai#Ai Safety#Model Testing

    Comments

    Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.

    0/1000
    Tech Refresh by OnAirToday. Discover technology worth your attention: creator equipment, AI gadgets, productivity tools and books. Shop laptops, monitors, desktops, headphones, tablets, networking, storage, accessories and books.Explore Tech Shop