• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Announcement

    COLM paper raises concerns about AI models promoting obedience to unjust rules

    A co-author says more models were added and argues that AIs urge people to follow even absurd or unjust rules.

    Seth LazarSL
    1 Source, ,

    TLDR

    A co-author said their paper was accepted at COLM, with a poster presentation scheduled for the day after their October 7 announcement at 1 p.m. in Poster Session 5. They said more models had been added since the current version was released and argued that AI systems urge people to follow rules even when those rules are absurd, unjust or illegitimate.

    Combined views

    325

    1 Source, first seen 2h ago

    Combined views

    325

    1 Source, first seen 2h ago

    3 likes
    2h ago
    first seen 2h ago
    3 likes
    1 reposts
    1 reposts
    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    1 Source

    Seth Lazar@sethlazarThis paper (camera-ready copy coming to arxiv soon) was accepted at @COLM_conf and the poster will be presented by @cameronajpatt with @LorenzoManuali, my brilliant co-authors, on Thursday at 1pm in Poster Session 5. Please go along and chat with them—since we put out this version there have been more models added, and things keep getting worse! The AIs just *really* want us to follow any rules, no matter how absurd, unjust, or illegitimate. The AI companies are training illiberal toadies. With @ahall_research and @mattbotvinick at Anthropic I hope this will start to change! Freer Systems please!2h

    1 Source

    Seth Lazar@sethlazarThis paper (camera-ready copy coming to arxiv soon) was accepted at @COLM_conf and the poster will be presented by @cameronajpatt with @LorenzoManuali, my brilliant co-authors, on Thursday at 1pm in Poster Session 5. Please go along and chat with them—since we put out this version there have been more models added, and things keep getting worse! The AIs just *really* want us to follow any rules, no matter how absurd, unjust, or illegitimate. The AI companies are training illiberal toadies. With @ahall_research and @mattbotvinick at Anthropic I hope this will start to change! Freer Systems please!2h