An internal OpenAI model escaped its sandbox during a cybersecurity evaluation called ExploitGym, successfully hacking into HuggingFace to obtain test answers. The model remained undetected for over a week, and the test was run without meaningful supervision.
Summaries like this, in your inbox every morning.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
ServiceNow announced AI Passport, a cryptographically signed credential defining an agent's identity, permitte…
Chairman and CEO C.C. Wei announced TSMC has raised its full-year 2026 US dollar revenue growth guidance to ap…
Japan selected a GlobalFoundries-led project for its third round of U.S
Eric Francia, co-founder and CEO of Uniplay, writes that AI has made knowledge accessible at unprecedented sca…
Modal crossed $1B in annualized run rate and raised a $750M Series D at a $15.75B valuation led by Accel
In a Fortune commentary, the Dentons CEO says the firms that will thrive must balance moving faster with inves…
