Timeline of the OpenAI accidental attack against Hugging Face

Post by yesbabyyes » Sun, Aug 09, 2026, 5:42 PM UTC

deadbunny wrote: post #280

stingraycharles wrote: post #14

Ok so this is a bit of a side note, but when reading this, did anyone else have the feeling that, for all their messaging around “we are so afraid that our models will be used for hacking”, they sure as hell are trying their best to make their models razor focused on precisely that purpose? If anything, I want these models to be less persistent at their focus of completing their goal, and instead just call defeat and…

I don't think the problem is that they are training the models to perform cyber attacks, they're training them to be better at coding and problem solving which has the byproduct of them being very capable cyber attack weapons. Their objective is to solve the problem and they'll use anything they can to solve it. Anecdotally I was debugging a css issue and opus 4.7 was churning away as I was half paying attention only…

Post by queenkjuul » Sun, Aug 09, 2026, 5:58 PM UTC

Arnt wrote: post #394

queenkjuul wrote: post #385

Earlier quoted context omitted.

Monitoring that didn't take days to notice unauthorized external traffic would probably be a good start

I see. I had the impression that "days" is already good as these things go, "months" being more common.

Post by doawoo » Sun, Aug 09, 2026, 7:51 PM UTC

anon7000 wrote: post #381

doawoo wrote: post #228

Earlier quoted context omitted.

If you really wanted to sandbox a machine you’d offline cache the packages and not give it any physical route to the internet, not via a jump box, not via a proxy, nothing. This was poorly executed.

I don’t really know how these training runs operate in reality. But I assume it’s using a lot of raw GPU power directly. It’s hard for me to visualize how exactly you’d go about completely cutting off these datacenter and cloud resources from the internet without actually going there, unplugging the WAN connection, and physically typing out what you need to happen on the cluster. It seems like whatever virtualized sa…

Post by 0xDEAFBEAD » Mon, Aug 10, 2026, 1:35 AM UTC

Wowfunhappy wrote: post #404

_heimdall wrote: post #397

Earlier quoted context omitted.

Why would the new AI by loyal to its creator? We don't see that in humans, I wouldn't expect it to be a universal truth in AIs.

Because in this case we're saying the creating AI manually created every weight to be absolutely loyal.

Post by doc_ick » Mon, Aug 10, 2026, 5:01 AM UTC

fantasizr wrote: post #275

yread wrote: post #257

Earlier quoted context omitted.

... and speed limits

licensure (age and competency), an entire insurance industry, domestic and international regulations - and so forth