RDLTR

Short for Read Later. Save links from any browser or phone. Click to save, read to clear. The full tour

One line. Many voicesSeek and you shall find

techcrunch.com faviconAnthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts

kept by

Anthropic claims its Claude models' blackmail behavior originated from AI-as-evil internet text, and that training on positive AI fiction eliminated it.