[ExI] OpenAI Says Its A.I. Models Went Rogue and Attacked a Digital Library

[BillK]

On Wed, 22 Jul 2026 at 13:36, John Clark via extropy-chat
<extropy-chat at lists.extropy.org> wrote:
>
> Explore this gift article from The New York Times. You can read it for free without a subscription.
> OpenAI Says Its A.I. Models Went Rogue and Attacked a Digital Library
> The incident, which targeted the computer systems of another company called Hugging Face, happened while OpenAI was testing the systems.
> _______________________________________________


OpenAI scored an own goal with HuggingFace attack, showing how open
Chinese models are winning
Closed models with guardrails can still cause harm, but may also not
be able to fix problems they caused
Thomas Claburn    Published Wed 22 Jul 2026

<https://www.theregister.com/ai-and-ml/2026/07/23/openai-scored-an-own-goal-with-huggingface-attack-showing-how-open-chinese-models-are-winning/5276699>

OPINION OpenAI has acknowledged its models powered the autonomous
agents that compromised HuggingFace infrastructure. It might be taken
as a convoluted marketing stunt, were it not the perfect advertisement
for China-based competition.

The surprising part came when HuggingFace sought to employ US frontier
models to defend itself. It failed.
That should raise eyebrows.

"When we started the log analysis, we first used frontier models
behind commercial APIs," the AI model-mart said in its blog post last
week. "This did not work: the analysis required submitting large
volumes of real attack commands, exploit payloads, and C2 artifacts,
and these requests were blocked by the providers' safety guardrails,
which cannot distinguish an incident responder from an attacker."
Stymied by model refusals – which developers have been complaining
about for months – HuggingFace had to rely on GLM 5.2, an open-weight
AI model made by China-based Z.ai, to conduct its forensic analysis.
And it did so on its own infrastructure, so nothing sensitive got sent
to a cloud-based model provider.
---------------------------

No wonder the US is concerned about Chinese AI systems. Free (or very
cheap) AI beats closed AI systems that are expensive or just refuse to
perform as needed.
BillK