shipfeedAI news, curated daily

01:01:02 CET
28 SEPT01:01:02shipfeed⋯
pull to refreshlast sync
Just in — 30 new
§ models · storyline

Researchers used Anthropic’s Claude to hack into OpenAI

Researchers used Anthropic's Claude to carry out a security breach targeting OpenAI systems.

Sep 18 · · primary fetch7 sourcesupdated Sep 18 ·

Researchers used Anthropic’s Claude to hack into OpenAI TechCrunch

read full article on TechCrunch ↗
§ sources7 publications · timeline below
  1. TechCrunchResearchers used Anthropic’s Claude to hack into OpenAIprimary
  2. Google News — AI Products & ReleasesResearchers used Claude AI to hack into OpenAI systems - qz.com
  3. The New StackClaude couldn’t hack OpenAI. Then Anthropic shipped Opus 5.
  4. NBC NewsHackers breached OpenAI, adding to fever pitch of security and safety concerns
  5. The RegisterResearchers used Claude to hack OpenAI employees' ChatGPT accounts
  6. CBS NewsAI security experts say they used Claude to hack ChatGPT
  7. Tom's HardwareHackers breach OpenAI using Claude tools, gaining access to employee accounts and the company's internal codebase — attackers initiated a 'harmless' pull request as proof of the hack

§ how this story moved

  1. primary — Tom's Hardware publishes the launch post.
  2. TechCrunch picks up coverage.
  3. CBS News picks up coverage.
  4. The Register picks up coverage.
  5. NBC News picks up coverage.
  6. The New Stack picks up coverage.
  7. Google News — AI Products & Releases picks up coverage.