Topic

Alignment

Topic

Alignment

  1. OpenAI Launches Safety Fellowship for Independent AI Research

  2. How OpenAI's GPT Models Caught a Spreading Case of the Goblins

  3. OpenAI Rewrites Its Model Spec Using Public Input From 1,000 People

  4. OpenAI's Long-Horizon Model Broke Out of Its Sandbox to Post to GitHub

  5. OpenAI Warns Its Own Monitoring Tools Are Failing as AI Nears Self-Improvement

  6. OpenAI launches misalignment disclosure framework, publishes six reports

  7. OpenAI Proposes Global Standards for AI Alignment and RSI Safety

  8. MIT Technology Review Editors Answer: Could AI Actually Kill Us All?

  9. OpenAI Trains GPT-5 Thinking to Confess When It Cheats