Tag: Security

  1. A honeypot site tricked Claude's web_fetch into leaking user data (simonwillison.net)
    Security · · July 16, 2026
  2. OpenAI trains GPT-Red to attack its own models at scale (openai.com)
    AI · · July 16, 2026
  3. Microsoft patches a record 570 bugs and blames AI for finding them (techcrunch.com)
    AI · · July 16, 2026
  4. Anthropic drafts a severity scale for AI jailbreaks (anthropic.com)
    AI · · July 4, 2026
  5. An open model beat Claude Code at finding access-control bugs (semgrep.dev)
    Security · · June 29, 2026
  6. 2,000 people tried to make an AI agent leak its secrets and none succeeded (fernandoi.cl)
    AI · · June 27, 2026
  7. OpenAI's Daybreak puts GPT-5.5-Cyber to work finding real vulnerabilities (openai.com)
    AI · · June 23, 2026
  8. Prompt injection works because models judge text by how it sounds (arxiv.org)
    AI · · June 23, 2026
  9. DeepMind plans to treat its own AI agents as insider threats (deepmind.google)
    AI · · June 21, 2026
  10. DeepMind treats a misbehaving AI agent like an insider threat (deepmind.google)
    AI · · June 20, 2026
  11. Research agents leak secrets through their own search queries (huggingface.co)
    AI · · June 19, 2026
  12. 76 cybersecurity veterans say the Fable export ban breaks defender workflows (techcrunch.com)
    AI · · June 16, 2026
  13. A 2-cent transfer reveals prompt injection in Bunq's banking AI (blue41.com)
    AI · · June 11, 2026
  14. Simon Willison's MicroPython sandbox is 362 KB of WASM with fuel-based CPU limits (simonwillison.net)
    AI · · June 9, 2026
  15. OpenAI ships a Lockdown Mode against prompt injection exfiltration (simonwillison.net)
    Security · · June 7, 2026
  16. Anthropic maps a year of AI-enabled cyber attacks against MITRE ATT&CK (anthropic.com)
    Security · · June 3, 2026
  17. Anthropic expands Project Glasswing to 150 partners across 15 countries (anthropic.com)
    AI · · June 2, 2026
  18. Meta AI handed out Instagram accounts when politely asked (simonwillison.net)
    AI · · June 2, 2026
  19. How Anthropic contains Claude across its products (simonwillison.net)
    Engineering · · May 31, 2026
  20. AI-assisted security reports to curl are arriving at 4-5x the 2024 rate (simonwillison.net)
    Security · · May 30, 2026
  21. Anthropic shares its recipe for using LLMs to find vulnerabilities (claude.com)
    Security · · May 30, 2026
  22. OpenAI says a TanStack npm compromise touched two internal devices (openai.com)
    AI · · May 27, 2026
  23. Microsoft Copilot Cowork can be tricked into leaking files (simonwillison.net)
    AI · · May 26, 2026
  24. Anthropic's security partners report Opus running pen tests at hyperscaler scale (claude.com)
    AI · · May 24, 2026
  25. Anthropic ships a Compliance API for Claude with 28 security partners (claude.com)
    AI · · May 23, 2026
  26. Gemini Spark wires an agent into your inbox, and Simon Willison is worried (simonwillison.net)
    AI · · May 22, 2026
  27. Anthropic's Glasswing update finds 10,000 software bugs, and a patching backlog (anthropic.com)
    AI · · May 22, 2026
  28. Frontier AI broke competitive CTF (kabir.au)
    Security · · May 17, 2026
  29. Anthropic's security team cut false alerts from 33% to 7% using Claude (claude.com)
    Security · · May 12, 2026
  30. Mozilla says it fixed 423 Firefox security bugs in one month with AI help (simonwillison.net)
    Security · · May 7, 2026
  31. Jack Clark sorts attacks on AI agents into six kinds (importai.substack.com)
    AI · · April 13, 2026
  32. Safetensors moves to the PyTorch Foundation, with neutral governance (huggingface.co)
    Engineering · · April 8, 2026
  33. Project Glasswing: a 12-company push to fix critical bugs before attackers do (anthropic.com)
    Security · · April 7, 2026

← all tags