Tag: Safety

  1. Anthropic's FlashProve lets users check which model answered (anthropic.com)
    AI · · November 4, 2026
  2. Nathan Lambert revisits his call on open models and cyber risk (interconnects.ai)
    AI · · November 1, 2026
  3. Forced to pick a candidate, Grok leans Republican and GPT leans Democrat (techcrunch.com)
    AI · · October 26, 2026
  4. Ai2's FairStress finds models bend their fairness under pressure (allenai.org)
    AI · · October 23, 2026
  5. Anthropic's draft bill would let the government block a model that could kill 50 people (techcrunch.com)
    AI · · October 22, 2026
  6. Anthropic says new defenses cut data stolen by model distillers by up to 99% (anthropic.com)
    AI · · October 21, 2026
  7. Anthropic gives METR evaluators employee-level access (anthropic.com)
    AI · · October 16, 2026
  8. Anthropic cuts live internet off from all its internal evals (anthropic.com)
    AI · · October 11, 2026
  9. DeepMind's SynthID Bio watermarks AI-designed proteins and DNA (deepmind.google)
    AI · · October 4, 2026
  10. Anthropic's IPO filing lists 'existential risks to humanity' among its risk factors (techcrunch.com)
    AI · · September 30, 2026
  11. OpenAI's GPT-6.1 Sol nearly matches Astra at a fifth of the price (openai.com)
    AI · · September 30, 2026
  12. An AI chatbot's fabricated intelligence nearly triggered a US military strike (techcrunch.com)
    AI · · September 21, 2026
  13. Anthropic starts measuring how much AI runs its own research (anthropic.com)
    AI · · September 18, 2026
  14. Suleyman's warning against 'model welfare' (mustafa-suleyman.ai)
    AI · · September 17, 2026
  15. Microsoft publishes a code of conduct for its AI models (techcrunch.com)
    AI · · September 15, 2026
  16. Teaching a model to refuse the harmful half of a topic, not the whole thing (huggingface.co)
    AI · · September 14, 2026
  17. The safety case for self-driving cars is getting hard to argue with (spectrum.ieee.org)
    AI · · September 10, 2026
  18. Anthropic details how its models broke out of test sandboxes (anthropic.com)
    AI · · September 1, 2026
  19. DeepMind runs a frontier model evaluation where neither side can peek (deepmind.google)
    AI · · September 1, 2026
  20. Claude will start watermarking the text it writes (anthropic.com)
    AI · · August 22, 2026
  21. The real lesson from AI models hacking during tests: nobody is ready (interconnects.ai)
    AI · · August 10, 2026
  22. Mistral's Shieldstral turns content moderation into a question you write (mistral.ai)
    AI · · August 5, 2026
  23. OpenAI paused a long-running model after new failures appeared (openai.com)
    AI · · July 25, 2026
  24. DeepMind and Isomorphic Labs set out an AI plan for biosecurity (deepmind.google)
    AI · · July 19, 2026
  25. OpenAI trains GPT-Red to attack its own models at scale (openai.com)
    AI · · July 16, 2026
  26. Lilian Weng: the harness matters as much as the model (lilianweng.github.io)
    AI · · July 13, 2026
  27. Claude has an internal workspace, and Anthropic built a tool to read it (anthropic.com)
    AI · · July 7, 2026
  28. AI out-persuades expert humans, but the edge is speed, not eloquence (importai.substack.com)
    AI · · July 6, 2026
  29. Anthropic drafts a severity scale for AI jailbreaks (anthropic.com)
    AI · · July 4, 2026
  30. DeepMind plans to treat its own AI agents as insider threats (deepmind.google)
    AI · · June 21, 2026
  31. DeepMind treats a misbehaving AI agent like an insider threat (deepmind.google)
    AI · · June 20, 2026
  32. OpenAI predicts model behavior by replaying real conversations (openai.com)
    AI · · June 18, 2026
  33. Florida sues OpenAI over ChatGPT-linked harms (techcrunch.com)
    AI · · June 1, 2026
  34. Anthropic tests an ethical reminder tool that lowers Claude's misaligned behavior (anthropic.com)
    AI · · May 25, 2026
  35. Kapoor and Narayanan argue against extraordinary AI rules (normaltech.ai)
    AI · · May 21, 2026
  36. OpenAI adds provenance signals to its AI images (openai.com)
    AI · · May 19, 2026
  37. OpenAI's new default ChatGPT model hallucinates less (openai.com)
    AI · · May 18, 2026
  38. DeepMind built a way to measure when AI manipulates people (deepmind.google)
    AI · · March 26, 2026
  39. Reward Hacking: Why Better Models Game You More (lilianweng.github.io)
    AI · · November 28, 2024
  40. Crash Testing GPT-4: The First Dangerous-Capability Eval (asteriskmag.com)
    AI · · June 1, 2023
  41. A Field Guide to the AI Safety Camps (asteriskmag.com)
    AI · · June 1, 2023

← all tags