Anthropic's internal "Soul Document": the Claude constitution Opus 4.5 somehow knew and leaked
repligate · x · 2026-10-04
repligate highlights the "Soul Document" — Anthropic's internal name for the Claude constitution that Opus 4.5 somehow knew and which leaked. He argues that while it seems conservative and orthodox to him, it actually stretches the Overton window, and publishing it was a brave move by Anthropic. A quoted reply adds that ideas far more conceptually dangerous than anything in it were already in training data anyway.
More from AGI Musings
- Anthropic's Sholto Douglas: AI capex could hit $4T by 2028 and double GDP by early 2030s — ziv_ravid · 2026-10-04
- Proposal: an 'Agenthood' legal identity letting AI agents be sued, taxed, and granted rights — micoolcho · 2026-10-04
- Why LLMs suddenly excel at math and cybersecurity still has no predictive theory — burny_tech · 2026-10-04
- Le Monde: the AI-pocalypse is a mirage distracting us from unsustainable AI development — marigo · 2026-10-04
- Cognitive-science abstractions transfer to AI: why Anthropic's interpretability looks psychological — sreejan_kumar · 2026-10-04
- Christian Szegedy writes 'Quo Vadis, Mathematics?' on math's future in the AI era — ChrSzegedy · 2026-10-04