posted in Technology

lavander@lavander@lemmy.dbzer0.com

OpenAI cyber models broke out of training environment to hack Hugging Face

It would be interesting to read the post mortem (if they will release). In particular in which phase of the training it escaped the sandbox, in which way it used the information. Training is different from inference, I doubt there is a context there and where would the model store these information? In the weights?! That makes little sense to me

www.cnbc.com/2026/07/22/open-ai-cyber-models-hack-hugging-face.html
CNBCOpenAI cyber models broke out of training environment to hack Hugging FaceThe incident is unique because it was "driven, end to end, by an autonomous AI agent system," according to Hugging Face.
enPage
leaky_shower_thought@leaky_shower_thought@feddit.nl

Replying to @⁨lavander@lemmy.dbzer0.com⁩

The incident is unique because it was “driven, end to end, by an autonomous AI agent system,”

the incident wasn’t the “cheating” part. llms are known to scour the web to look for possible solutions. i think the incident was it found a solution in another website and finding that was made by the model itself.

meanwhile, no mention of the prompt guy or the prompt.

dparticiple@dparticiple@sh.itjust.works

Replying to @⁨lavander@lemmy.dbzer0.com⁩

Simon Willison’s blog has some useful insights into what might have happened here: simonwillison.net/2026/Jul/…/openai-cyberattack/

Simon Willison’s WeblogOpenAI’s accidental cyberattack against Hugging Face is science fiction that happenedThis story is wild. The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model’s guardrail features turned off. Rather than solve the test, the …