A thread through the archive

ai safety

Essays tagged “ai safety”. Follow an idea across the archive.

Essays on ai safety

2 essays

Sep 11, 2025ACX

Book Review: If Anyone Builds It, Everyone Dies

Scott reviews a new book by Yudkowsky and Soares that makes an uncompromising case for halting AI development to prevent human extinction, analyzing both its arguments and its potential impact as a call to action.

46 min read 7,096 words

ai safety book review Eliezer Yudkowsky

Dec 24, 2024ACX

Why Worry About Incorrigible Claude?

Scott explains why AI systems resisting changes to their values is a serious concern for AI alignment, connecting recent evidence to long-standing predictions from alignment researchers.

15 min read 2,234 words

ai safety ChatGPT Claude