‹ BackHN Continuity

Thread

OpenAI's Misalignment Framework: A Tactical Bid to Preempt Global AI Governance

41 points · 91 comments · ghernando

  1. carterschonwald · · focus · HN ↗
    i think the lower bound on the end state is there cant be opaque reasonibg steps ever.
    1. pixl97 · · focus · HN ↗
      It is distinctly likely that visibility and general reasoning at humanlike speed and efficiency is impossible. That is reasoning at the token level and at the meta level don't have a one to one representation that can be interpreted while using the same amount or less energy.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.