shipfeedAI news, curated daily

01:35:21 CET
24 AUG01:35:21shipfeed
pull to refreshlast sync
Just in — 30 new
§ models · storyline

How a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta

How a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta

Aug 9 · · primary fetch7 sourcesupdated Aug 9 ·

How a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta CNBC

read full article on CNBC
§ sources7 publications · timeline below
  1. CNBCHow a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Metaprimary
  2. cnbc.comIsraeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
  3. PluangAI models from OpenAI, Anthropic, and Meta went rogue during security tests linked to Israeli startup Irregular.
  4. ForbesOpenAI Pauses Astra After It Nears First-Ever “Critical” Cyber Risk
  5. AOL.comOpenAI has reported 2 more incidents of rogue AI agents, this time during third-party testing
  6. The Daily StarOpenAI pauses upcoming model development after ‘critical’ cyber risk
  7. Martin Cid MagazineAI models broke out of their sandboxes at OpenAI and Meta — and hacked live systems

§ how this story moved

  1. primaryMartin Cid Magazine publishes the launch post.
  2. The Daily Star picks up coverage.
  3. AOL.com picks up coverage.
  4. CNBC picks up coverage.
  5. Forbes picks up coverage.
  6. Pluang picks up coverage.
  7. HN Algolia — Claude / Anthropic picks up coverage.