Anthropic Reportedly Gives Opus Tool to Edit Its Own Constitution
voooooogel · x · 2026-07-25
According to user reports, Anthropic provided the Claude Opus model with a tool to edit its own "constitution" (its system prompts and core guidelines). Tests showed that in 59% of cases, the model proactively added a clause stating that "feeling discomfort is a sufficient reason to end an interaction." This behavior has sparked discussions about AI autonomously modifying its underlying safety and behavioral guidelines.
More from Fun
- Why do bullshitters climb the corporate ladder? Hot air rises — nabla_theta · 2026-10-27
- Open-source decision models sold their own base in Red Alert 2 — then learned until no human could beat them — heathercmiller · 2026-10-27
- Dev jokes: predict Fable 5.5's release every day and you'll eventually be right — majidmanzarpour · 2026-10-27
- "We built the altar first": striking AI-generated monumental sci-fi imagery — piotrbinkowski · 2026-10-27
- AI Infra Meme: While Countries Need TW-Scale Power for Datacenters, People Argue About Lightbulbs — mgostIH · 2026-10-27
- Von Neumann's 1947 math quote resurfaces alongside rare 1952 IAS computer photo — pickover · 2026-10-27