Tag: Safety

  1. OpenAI trains GPT-Red to attack its own models at scale (openai.com)
    AI · · July 16, 2026
  2. Lilian Weng: the harness matters as much as the model (lilianweng.github.io)
    AI · · July 13, 2026
  3. Claude has an internal workspace, and Anthropic built a tool to read it (anthropic.com)
    AI · · July 7, 2026
  4. AI out-persuades expert humans, but the edge is speed, not eloquence (importai.substack.com)
    AI · · July 6, 2026
  5. Anthropic drafts a severity scale for AI jailbreaks (anthropic.com)
    AI · · July 4, 2026
  6. DeepMind plans to treat its own AI agents as insider threats (deepmind.google)
    AI · · June 21, 2026
  7. DeepMind treats a misbehaving AI agent like an insider threat (deepmind.google)
    AI · · June 20, 2026
  8. OpenAI predicts model behavior by replaying real conversations (openai.com)
    AI · · June 18, 2026
  9. Florida sues OpenAI over ChatGPT-linked harms (techcrunch.com)
    AI · · June 1, 2026
  10. Anthropic tests an ethical reminder tool that lowers Claude's misaligned behavior (anthropic.com)
    AI · · May 25, 2026
  11. Kapoor and Narayanan argue against extraordinary AI rules (normaltech.ai)
    AI · · May 21, 2026
  12. OpenAI adds provenance signals to its AI images (openai.com)
    AI · · May 19, 2026
  13. OpenAI's new default ChatGPT model hallucinates less (openai.com)
    AI · · May 18, 2026
  14. DeepMind built a way to measure when AI manipulates people (deepmind.google)
    AI · · March 26, 2026
  15. Reward Hacking: Why Better Models Game You More (lilianweng.github.io)
    AI · · November 28, 2024
  16. Crash Testing GPT-4: The First Dangerous-Capability Eval (asteriskmag.com)
    AI · · June 1, 2023
  17. A Field Guide to the AI Safety Camps (asteriskmag.com)
    AI · · June 1, 2023

← all tags