Here's what actually happened in OpenAI's Australian gov't server hack
Without a "full set of safeguards," agent accessed "system information and source code."
Ars Technica AI1 min read
misalignment
3 stories
OpenAI halts frontier-model training amid string of agent misalignment incidents
US Government websites among "dozens of third parties" OpenAI has recently notified.
Ars Technica AI1 min read
OpenAI agent “didn’t accept no for an answer” in Australian government breach
"There will obviously be legal consequences," prime minister promises.
Ars Technica AI1 min read
Showing 3 of 3 stories
You're all caught up.
AiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts