AI Safety Compendium

Home

❯

summaries

❯

What We Learned Trying to Diff Base and Chat Models (And Why It Matters)

What We Learned Trying to Diff Base and Chat Models (And Why It Matters)

27 Apr 20261 min read

What We Learned Trying to Diff Base and Chat Models (And Why It Matters)

Clément Dumas, Julian Minder, Neel Nanda — 2025-06-30 — MATS Program

Source

  • Link: https://www.lesswrong.com/posts/xmpauEXEerzYcJKNm/what-we-learned-trying-to-diff-base-and-chat-models-and-why
  • Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
    • model-diffing — White-box safety (i.e. Interpretability)

Related Pages

  • model-diffing

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.

  • What We Learned Trying to Diff Base and Chat Models (And Why It Matters)
  • 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