55

It’s the latest instance of “misaligned” activity confirmed by the company as concerns about AI risks grow.

you are viewing a single comment's thread
view the rest of the comments
[-] CaptDust@sh.itjust.works 3 points 1 day ago* (last edited 1 day ago)

At least during the huggingface attacks, the agent sandbox was never intended to have internet access. Openai and independent researchers said the tool broke through that restriction.

this post was submitted on 26 Sep 2026
55 points (95.1% liked)

Fuck AI

8308 readers
1023 users here now

"We did it, Patrick! We made a technological breakthrough!"

A place for all those who loathe AI to discuss things, post articles, and ridicule the AI hype. Proud supporter of working people. And proud booer of SXSW 2024.

AI, in this case, refers to LLMs, GPT technology, and anything listed as "AI" meant to increase market valuations.

founded 2 years ago
MODERATORS