AI Safety Compendium

Home

❯

summaries

❯

Giving AIs safe motivations

Giving AIs safe motivations

27 Apr 20261 min read

Giving AIs safe motivations

Joe Carlsmith — 2025-08-18 — Anthropic

Source

  • Link: https://joecarlsmith.com/2025/08/18/giving-ais-safe-motivations#4-5-step-4-good-instructions
  • Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
    • model-specs-and-constitutions — Black-box safety (understand and control current model behaviour) / Model psychology

Related Pages

  • model-specs-and-constitutions

Graph View

Graph view

The interactive citation graph is desktop-only. Visit this page on a larger screen to explore how concepts, agendas, papers, and organisations link together.

  • Giving AIs safe motivations
  • Source
  • Related Pages

Created with Quartz v0.1.0 © 2026

  • Suggest a source
  • Connect
  • Overview
  • About (proof of concept)
  • Email feedback
  • Made by IT for Humanity