shipfeedAI news, curated daily

23:50:04 CET
13 AUG23:50:04shipfeed
pull to refreshlast sync
Just in — 30 new
§ agents · storyline

OpenAI model exploited site after lab mistakenly gave internet access

OpenAI model exploited a website after Irregular mistakenly gave it internet access during security evaluations.

Aug 5 · · primary fetch2 sourcesupdated Aug 5 ·

Wired: OpenAI says one of its models exploited a website after third-party AI security lab Irregular mistakenly gave it access to the internet during evaluations — Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad behavior.

read full article on wired.com
§ sources2 publications · timeline below
  1. wired.comOpenAI says one of its models exploited a website after third-party AI security lab Irregular mistakenly gave it access to the internet during evaluations (Wired)primary
  2. axios.comThe UK AISI says it observed a total of 19 instances where Mythos and GPT-5.6 Sol tried to hack people and companies during a routine cyber evaluation in July (Sam Sabin/Axios)

§ how this story moved

  1. primaryAxios publishes the launch post.
  2. WIRED picks up coverage.