PulseAugur
EN
LIVE 00:52:30

AI philosophy: Distinguishing true optimizers from descriptive optimization

This post explores the philosophical distinction between a system that is merely described as optimizing and a true optimizing agent. It questions whether there's a universally accepted threshold for classifying a system as an agent pursuing an outcome, or if this distinction is inherently relative to the observer. The discussion stems from observations within AI control discussions on LessWrong. AI

IMPACT Explores fundamental questions about AI agency and optimization, relevant for theoretical AI safety discussions.

RANK_REASON The cluster discusses a philosophical distinction related to AI, presented as a question on a forum, rather than a concrete development or release.

Read on LessWrong (AI tag) →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. LessWrong (AI tag) TIER_1 English(EN) · stewart leland jansen ·

    What Separates an Optimizer From Something We Merely Describe as Optimizing?

    <p><span>Reading through the AI Control posts, I notice that much if the discussion assumes a distinction between a system executing a policy and a system pursuing an outcome despite constraints. </span></p><p><span>Is there a generally accepted threshold where LessWrong would sa…