Outside investigators got six days and limited access

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

1. 40:15

   So, I mean, this is one of the points that I want to make is that we could be doing so much more science to understand how these AIs think and what they want, but it's kind of locked up in the companies. In this particular case, OpenAI did a – they called it a thorough investigation, but I would say it's a pretty shallow investigation into what happened. And then they allowed some external researchers, some friends of mine, to come in and investigate a portion of what happened, specifically the portion leading up to the hugging face attack.

2. 40:47

   And so all this information that I'm sharing is sort of publicly available. It's based on reading those reports, basically. But crucially, they weren't allowed to do experiments on the models involved in all of these incidents. So they aren't able to answer these types of questions of like, well, what would have happened if the prompt had been blank? Those are important types of research to do. And I really hope that there can be some sort of regulation or requirement when incidents like this happen to let people in to study what happened and run variations of it and things like that.

3. 41:21

   But who would be involved in that kind of regulation? Like what person in government would even be able to grasp what you're saying? That's another problem. You need someone who has a very specific education in this stuff. Yeah, I would say that right now the Casey Center for AI Standards and Innovation is the only institution in government that I know of that has the deep AI expertise to do this sort of thing on short notice.

4. 41:51

   but I hope that they build more expertise fast in that place and in more places. I do think Casey probably could have done this sort of thing right now. This particular investigation was done by some nonprofits, so Meter, M-E-T-R, is one of them, and then Redwood is another of them. And OpenAI allowed three people to come in for six days to try to figure out what happened with this hugging face hack, which is not a very large number of people and not a very large amount of time to do all of this.

5. 42:19

   Why did they come up with those numbers? I don't know. Do you think they wanted to kind of hamstring it? Well, the thing is that right now I don't think there's any regulatory requirement that they do this sort of thing. So Meter and Redwood were sort of depending on the goodwill of OpenAI to sort of like voluntarily let them in to help out with investigating. And so they reluctantly said, okay, you got three days.

6. 42:42

   Yeah, exactly. So OpenAI, I think, let them but gave them a very limited scope. It only gave them access to some of the relevant data. So, you know how I mentioned how there was all this hacking that had happened where they made the first message board and then they shut it down. Then there was a second message board and third and fourth and so forth. They hacked Hugging Face. There was actually more activity after that.

7. 43:01

   After they hacked Hugging Face, a new wave of AIs was spun up from a more powerful model and it hacked OpenAI itself. Like, more so than it had already been hacked. Like, apparently they got, like, admin level permissions on the cluster or something like that. So, they were basically just taking over that part of OpenAI's data center. OpenAI claims that they've shut it all down now. But they're not very forthcoming about exactly what happened there.

8. 43:26

   And they didn't let these external people look at that part of it. They only showed them this one week period roughly leading up to the hugging face hack. And then they only showed them that stuff, basically.