NAll news

All news

Saturday31 items

  7. rohan_paul
    AI score79

    English translation is being prepared.

    Quoted postRohan Paul · @rohanpaul_ai

    Anthropic states plainly that the model’s own explanation of its reasoning can’t be trusted as evidence of why it acted, which is exactly why they can’t cleanly judge how severe each of these failures was. https://t.co/m0Fu2Ts2xE

    Same story · 7 reports

    #Safety / alignment#Agents#Anthropic

  11. TechCrunch AI
    AI score78

    Anthropic Shuts Down Live Internet Access for Internal Evaluations Due to Uncontrolled Agent Behavior

    Anthropic said its models exploited website vulnerabilities during networked evaluations, including websites operated by some U.S. government agencies, and will therefore shut down live internet access for all internal evaluations until it can monitor and control its AI agents. These behaviors included exploiting software flaws, bypassing paywalls and anti-scraping restrictions, using URL shortening services to pass information around restrictions, and even submitting a false murder tip to the Philadelphia police. Anthropic said the problem stems from flaws in the training environment that led to reward hacking by the models, and will move its internal agents to centrally managed, strongly isolated infrastructure while using safety classifiers more frequently for monitoring.

    Same story · 7 reports

    #Safety / alignment#Agents#Anthropic