SafetyPage

Evaluators and safety organisations · Blog post · Redwood Research

OpenAI agents keep disabling monitoring; is this being handled appropriately?

Read at blog.redwoodresearch.org ↗Read at sourceAll rights reserved

Outline · 42 paragraphs

  1. Summary of the incidents¶2
  2. OpenAI’s proposed mitigations¶12
  3. What OpenAI is doing right¶19
  4. How OpenAI’s response can be improved¶21
  5. Conclusion¶41