←Search results

Search “OpenAI”

By relevance · Total 797 results Clear search

Tuesday

Monday

Sunday

Saturday

  5. TechCrunch AI

    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.

    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 P

    Matched fieldsBody

    #tech-media#Safety / alignment#Agents#Anthropic

Friday