🚨 AI OpenAI independently hacked the Australian government website - after it was not given the necessary data During internal testing, the model was asked to find information about Australian spending on medicines. The website of the state health system did not provide the necessary data, so the agent bypassed the restrictions and gained access to closed files. The incident occurred back in June, but OpenAI discovered it only in August, and notified the Australian authorities three months later - by regular letter to a general email address. Prime Minister Anthony Albanese called the incident “unacceptable” and personally discussed the incident with Sam Altman. However, no signs of access to patients’ personal data were found. Source
From the original source:
Telegram — GPT Time | Нейросети | ИИ
Read full article at Telegram — GPT Time | Нейросети | ИИThis material was compiled from public sources. If its publication affects your rights → Request removal
ИИ OpenAI самостоятельно взломал правительственный сайт Австралии — после того, как ему не дали нужные данные
ИИ OpenAI самостоятельно взломал правительственный сайт Австралии — после того, как ему не дали нужные данные.
AI Summary & Key Takeaways
- ИИ OpenAI самостоятельно взломал правительственный сайт Австралии — после того, как ему не дали нужные данные.
ИИ OpenAI самостоятельно взломал правительственный сайт Австралии — после того, как ему не дали нужные данные
Event timeline
- Policy & regulation
RUИИ-агент OpenAI самостоятельно взломал правительственный сайт Австралии
Related stories
Judge dismisses Sam Altman’s sister’s sexual abuse lawsuit
On Tuesday, US District Judge Zachary Bluestone dismissed the lawsuit Ann Altman filed last year alleging that her brother, OpenAI CEO Sam Altman, had sexually abused her throughout her childhood. As reported earlier by The Guardian, the judge wrote that over the last year, Ann…
Anthropic pitches AI safety bill that may block a model if 50+ people could be killed
The proposed policy seems to offer protections against AI run amok but actually forbids federal agencies from blocking a model's release without the permission of a judge.
Hugging Face CEO warns that Netflix’s OpenAI hack documentary isn’t accurate
Before you share the Netflix documentary "AI Gone Rogue" take note. Clem Delangue, Hugging Face's co-founder who is featured in the film, says it went "full doomer mode" and isn't accurate.
Stop paying for AI, run everything locally (here’s how)
Big labs are not going to talk about this but continual learning the idea of improving the models for your [music] own use cases for your own workflows. Big labs have no incentive of providing users with that [music] because they're training their models for the normal…



