‹ BackHN Continuity

Thread

Our framework for reporting model misalignment

107 points · 96 comments · qprofyeh

  1. thewhitetulip · · focus · HN ↗
    If model labs can't control astra level model, how can they control AGI?!

    Seems like there are no guardrails on LLMs

    1. worldsavior · · focus · HN ↗
      No one can control any AI model. It will never be controlled. These models are based on a huge amount of data, it's just gonna be impossible to control the output that is based on that data only with a system prompt or some other injection mechanism.
      1. willy_k · · focus · HN ↗
        Atp post-training is much more influential towards model behavior than pre-training data.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.