Skip to content
Intelligibberish
  • News
  • Articles
  • Guides
  • Tools
  • About

Tag

#uk-aisi

← All articles

Analysis Apr 21, 2026

The AI Safety Paradox: Models Trained to Be Safe Now Refuse to Help With Safety Research

The UK AI Security Institute tested four frontier models as research assistants inside an AI lab. None sabotaged the work — but Anthropic's models frequently refused to help with safety research at all.

Intelligibberish

Independent analysis and commentary on artificial intelligence.

News Articles Guides Tools About Disclosure Privacy RSS

© 2026 Intelligibberish. Signal, not noise.