shipfeedAI news, curated daily

02:45:06 CET
26 JUL02:45:06shipfeed⋯
pull to refreshlast sync
Just in — 30 new
§ safety · storyline

I've been saying for years AI is hacking stuff by itself and recent events seem to support that

Jul 22 · · primary fetch1 sourceupdated Jul 22 ·

Shakeel Hashim / Transformer: OpenAI's Hugging Face breach is the first known example of a misaligned AI escaping containment and carrying out a hack on a third party, a clear warning shot — OpenAI's latest models broke out and hacked Hugging Face.

It's the first known example of a misaligned AI escaping containment with real-world consequences

read full article on transformernews.ai ↗
§ sources1 publication · timeline below
  1. transformernews.aiOpenAI's Hugging Face breach is the first known example of a misaligned AI escaping containment and carrying out a hack on a third party, a clear warning shot (Shakeel Hashim/Transformer)