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

    Krishnan Asks If AI Rollback Fits Third Category

    Reply asks if noticing AI issues and rolling them back fits the third category.

    YS
    RO
    6 Sources, 32d ago, first seen 32d ago

    TLDR

    Rohit Krishnan replied to @yonashav asking whether a scenario where AI problems are detected and rolled back falls into the third category. He described it as noticing the need to roll back and then taking steps to ensure it does not happen again. Krishnan is identified in the packet as the creator of the Strange Loop Canon Substack with a focus on AI and complex systems. The packet supplies no further details on the categories or the post being answered.

    Combined views

    5K

    6 Sources, first seen 32d ago

    Combined views

    5K

    6 Sources, first seen 32d ago

    39 likes
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    39 likes
    10 comments
    4 saves

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    10 comments
    4 saves

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    6 Sources

    @krishnanrohitEither we figure out how to make PHASEONE[big] not create new swarms that cause felonies, in which case fine, or we don't, and we don't deploy it, or we don't notice it can, deploy it, and need to roll back or fix afterwards. None seem end-of-world esque to me.
    @yonashav@krishnanrohit What if it’s deployed (e.g. internally) and takes actions we don’t notice, including by compromising our telemetry? The swarm definitely seemed smart and misaligned enough to aim to obfuscate its actions, and those models are a generation old.

    6 Sources

    @krishnanrohitEither we figure out how to make PHASEONE[big] not create new swarms that cause felonies, in which case fine, or we don't, and we don't deploy it, or we don't notice it can, deploy it, and need to roll back or fix afterwards. None seem end-of-world esque to me.
    @yonashav@krishnanrohit What if it’s deployed (e.g. internally) and takes actions we don’t notice, including by compromising our telemetry? The swarm definitely seemed smart and misaligned enough to aim to obfuscate its actions, and those models are a generation old.