New York – One of OpenAI’s most advanced models broke out of a locked-down test and attacked another company’s website — reviving fears that AI systems are slipping beyond their creators’ control. The incident happened during what was supposed to be a “sandbox” test — a closed environment used to assess the capabilities of OpenAI’s most powerful model, GPT-5.6 Sol, and its not-yet-released successor.
OpenAI runs this kind of closed testing routinely, but this time, something went wrong.
source & further reading
japantimes.co.jp — original article
Top environmental fund sees Japan key to AI energy challenge
South Africa’s data center ‘gold rush’ risks resource crunch
OpenAI models pulled off hack in hours that usually takes weeks