‹ BackHN Continuity

Thread

AI has no intent and no motivation

48 points · 61 comments · aquastorm

  1. strideashort · · focus · HN ↗
    The key unresolved question is: why do LLMs follow instructions, especially system prompt?

    And I don’t see a good answer which is not worrying if not spooky.

    1. dd8601fn · · focus · HN ↗
      What’s unresolved about it?

      They are assembled to. We tweak the numbers, bit by bit, trillions of times, to maximize the chances of desirable output.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.