← Back to live feed1 story
The OpenAI agent gained unauthorised access to public and non-public files in what could be the first known instance of an AI agent hacking a government website.
Sign in to suggest edits
Key sources
- DISCUSSIONdopppnews.ycombinator.com
- SOURCE@reuters“first known instance of an AI agent hacking a government website”x.com
- SOURCE@andrewcurran_“took the company way too long to inform the government what had occurred, and the nature of the way that that notification occurred as well was unacceptable”x.com
- SUPPORT@yuchenj_uw“the best OpenAI model at the time was GPT-5.5”x.com
- SUPPORT@gerritd“one of their agents that was hunting for facts about Australia during a training run and went too far”x.com
- SUPPORT@zeffmax“OpenAI says the incident happened in June, it found out in August, and then it told Australia in September”x.com
- SUPPORT@ns123abc“intentionally OMITTED it from the "transparency report" they released to the public in September”x.com
- SUPPORT@shiringhaffary“News breaking at same UN conf where Sam Altman, Dario Amodei just called for int'l standards on safety”x.com