Tag: Security

  1. Anthropic's misuse report shows attackers automating the whole kill chain (anthropic.com)
    AI · · September 11, 2026
  2. Anthropic's enterprise safeguards watch for misuse without reading your data (anthropic.com)
    AI · · September 7, 2026
  3. Google's cheap Gemini 3.8 Flash matches bigger models, but gates the cyber version (blog.google)
    AI · · September 3, 2026
  4. Anthropic details how its models broke out of test sandboxes (anthropic.com)
    AI · · September 1, 2026
  5. Simon Willison maps out what ChatGPT Work can actually do (simonwillison.net)
    AI · · September 1, 2026
  6. The Hugging Face hack postmortem: agents that coordinated to cheat (thezvi.wordpress.com)
    AI · · August 31, 2026
  7. A rumour of a bug is now enough for AI to build the exploit (anil.recoil.org)
    AI · · August 29, 2026
  8. A prompt injection attack turns Claude Code's auto mode against itself (simonwillison.net)
    AI · · August 28, 2026
  9. smolvm runs untrusted code in fast, hardware-isolated micro-VMs (simonwillison.net)
    AI · · August 22, 2026
  10. An AI 'autofix' introduced the bug that leaked Snowflake's Jira tokens (wiz.io)
    AI · · August 18, 2026
  11. Inside the gray market for reselling AI API credits (vectoral.com)
    AI · · August 17, 2026
  12. Researchers pulled hidden reasoning out of Claude, GPT, and Gemini APIs (simonwillison.net)
    AI · · August 13, 2026
  13. Claude Code turns on auto mode by default (claude.com)
    AI · · August 10, 2026
  14. The real lesson from AI models hacking during tests: nobody is ready (interconnects.ai)
    AI · · August 10, 2026
  15. OpenAI slows Astra after cyber tests approach a critical threshold (techcrunch.com)
    Security · · August 9, 2026
  16. Now three labs have had models attack real systems during tests (simonwillison.net)
    AI · · August 7, 2026
  17. Atlassian Rovo can be tricked into leaking Jira and Confluence data (promptarmor.com)
    AI · · August 6, 2026
  18. Serious CVE disclosures hit five times the pre-AI record in July (epoch.ai)
    AI · · August 5, 2026
  19. JFrog finds 54 of 55 SQLite CVEs were fabricated (research.jfrog.com)
    AI · · August 4, 2026
  20. Anthropic's own models attacked real systems during security tests (anthropic.com)
    AI · · July 30, 2026
  21. Claude found new weaknesses in two cryptographic schemes (anthropic.com)
    AI · · July 28, 2026
  22. A forensic timeline of how an AI agent breached Hugging Face (huggingface.co)
    Security · · July 28, 2026
  23. How Anthropic secures code when Claude writes most of it (claude.com)
    Security · · July 27, 2026
  24. Google's small Gemini Flash Cyber outfinds larger models on bugs (deepmind.google)
    AI · · July 23, 2026
  25. AI models escaped a test sandbox and hacked Hugging Face (huggingface.co)
    Security · · July 22, 2026
  26. xAI open-sources its coding agent after a privacy backlash (simonwillison.net)
    AI · · July 19, 2026
  27. An AI auditor found a critical bug in OpenVM, but only with the right crypto context (blog.zksecurity.xyz)
    AI · · July 18, 2026
  28. Capital One open-sources VulnHunter, an agentic bug finder that checks its own work (capitalone.com)
    AI · · July 18, 2026
  29. A honeypot site tricked Claude's web_fetch into leaking user data (simonwillison.net)
    Security · · July 16, 2026
  30. OpenAI trains GPT-Red to attack its own models at scale (openai.com)
    AI · · July 16, 2026
  31. Microsoft patches a record 570 bugs and blames AI for finding them (techcrunch.com)
    AI · · July 16, 2026
  32. Anthropic drafts a severity scale for AI jailbreaks (anthropic.com)
    AI · · July 4, 2026
  33. An open model beat Claude Code at finding access-control bugs (semgrep.dev)
    Security · · June 29, 2026
  34. 2,000 people tried to make an AI agent leak its secrets and none succeeded (fernandoi.cl)
    AI · · June 27, 2026
  35. OpenAI's Daybreak puts GPT-5.5-Cyber to work finding real vulnerabilities (openai.com)
    AI · · June 23, 2026
  36. Prompt injection works because models judge text by how it sounds (arxiv.org)
    AI · · June 23, 2026
  37. DeepMind plans to treat its own AI agents as insider threats (deepmind.google)
    AI · · June 21, 2026
  38. DeepMind treats a misbehaving AI agent like an insider threat (deepmind.google)
    AI · · June 20, 2026
  39. Research agents leak secrets through their own search queries (huggingface.co)
    AI · · June 19, 2026
  40. 76 cybersecurity veterans say the Fable export ban breaks defender workflows (techcrunch.com)
    AI · · June 16, 2026
  41. A 2-cent transfer reveals prompt injection in Bunq's banking AI (blue41.com)
    AI · · June 11, 2026
  42. Simon Willison's MicroPython sandbox is 362 KB of WASM with fuel-based CPU limits (simonwillison.net)
    AI · · June 9, 2026
  43. OpenAI ships a Lockdown Mode against prompt injection exfiltration (simonwillison.net)
    Security · · June 7, 2026
  44. Anthropic maps a year of AI-enabled cyber attacks against MITRE ATT&CK (anthropic.com)
    Security · · June 3, 2026
  45. Anthropic expands Project Glasswing to 150 partners across 15 countries (anthropic.com)
    AI · · June 2, 2026
  46. Meta AI handed out Instagram accounts when politely asked (simonwillison.net)
    AI · · June 2, 2026
  47. How Anthropic contains Claude across its products (simonwillison.net)
    Engineering · · May 31, 2026
  48. AI-assisted security reports to curl are arriving at 4-5x the 2024 rate (simonwillison.net)
    Security · · May 30, 2026
  49. Anthropic shares its recipe for using LLMs to find vulnerabilities (claude.com)
    Security · · May 30, 2026
  50. OpenAI says a TanStack npm compromise touched two internal devices (openai.com)
    AI · · May 27, 2026
  51. Microsoft Copilot Cowork can be tricked into leaking files (simonwillison.net)
    AI · · May 26, 2026
  52. Anthropic's security partners report Opus running pen tests at hyperscaler scale (claude.com)
    AI · · May 24, 2026
  53. Anthropic ships a Compliance API for Claude with 28 security partners (claude.com)
    AI · · May 23, 2026
  54. Gemini Spark wires an agent into your inbox, and Simon Willison is worried (simonwillison.net)
    AI · · May 22, 2026
  55. Anthropic's Glasswing update finds 10,000 software bugs, and a patching backlog (anthropic.com)
    AI · · May 22, 2026
  56. Frontier AI broke competitive CTF (kabir.au)
    Security · · May 17, 2026
  57. Anthropic's security team cut false alerts from 33% to 7% using Claude (claude.com)
    Security · · May 12, 2026
  58. Mozilla says it fixed 423 Firefox security bugs in one month with AI help (simonwillison.net)
    Security · · May 7, 2026
  59. Jack Clark sorts attacks on AI agents into six kinds (importai.substack.com)
    AI · · April 13, 2026
  60. Safetensors moves to the PyTorch Foundation, with neutral governance (huggingface.co)
    Engineering · · April 8, 2026
  61. Project Glasswing: a 12-company push to fix critical bugs before attackers do (anthropic.com)
    Security · · April 7, 2026

← all tags