“OpenAI’s Model Hacked Us” - Hugging Face’s Thomas Wolf
Episode publishedPodcast: The MAD Podcast with Matt Turc...The MAD Podcast with Matt Turck
Transcript preview
Preview only
You kinda have to move fast. It's a matter of at least hours and even more minutes. So you don't have time to apply for cybersecurity programs. The model was not at all tasked with attacking us, but decided to do that as a side quest of something else. They created fake accounts, fake GitHub account, trying to attack the sandbox by Blackmailing. That's a very different level, I think, of thinking. I could have been the target of this side quest of the model, basically. Yeah. That was very interesting artist, very, very scary.
Hi. I'm Matt Turk. Welcome back to the MAD Podcast. Today, my guest is Thomas Wolfe, co founder and chief science officer at Hugging Face. We unpack what might be the biggest AI story of the summer, how an open AI powered agent Hugging Face during cyber testing, and why an open source model helped the team fight back. We also explore model alignment, the future of Western open source AI, and the race towards recursive self improvement. Please enjoy this fantastic conversation with Thomas Wolfe. To take things in order, so the OpenAI hack. So I I know some of it is still being unpacked. I think
Yeah. For sure. I mean, typically, happened is now about three weeks ago in July 11, we started to have some, you know, strong hint that hacker was trying to penetrate that infrastructure. So for context, we are pretty visible in the AI world. We're pretty yeah, well-being central now in the tech world. We're pretty central in the tech world. So we do have, you know, regular occurrence of people trying to hack into our platform. That's a common thing since, I mean, I would say in the past two years, something that we've strongly upped our security team. We now have a serious team. So we're kin
So to unpack some of this, so you, alluded to the fact that to be able to defend yourself, the closed source models were not available, and, that's the, you know, sentence you tweeted that, and that's, you know, one of the key aspects of this, which is so fascinating, which is like the I think you said the first autonomous AI attack was carried out by a closed model and defended against with an open one, which is basically the the reverse or what everybody thought. So can you can you unpack that? What did you guys do? How did you go about it? And what does that mean for open source?
Yeah, I mean, what happened in the So we have a couple of like traditional cybersecurity protections, so like WIIS or Amazon, like we use a range of them, but we also have a stack like many people who is mostly based around plot code right now, which we use for many things. We use that for deploying, we use that for coding, but we use like also for operating and processing. And in this case, it's not only that Fable told us, I'm not allowed to touch cybersecurity, but also Opus, which was the fallback was saying, no, I'm also not touching these things. So basically the end was just say, won't
To make sure I got it right, so what you're saying is that to some extent it's open source versus closed source, but it's more the state of the world as of right now, like the way the current closed source models are designed or the current open source models are designed versus anything that's intrinsic to, one or the other. It so happens that the open source models right now are designed in a way where their guidelines or alignment philosophy allows them to be more reactive to a cyber attack. Is that correct?
Yeah. I think for many aspects, I think the close open distinction is almost orthogonal to the safe and safe. People don't understand that easily because it's easie
Keep exploring with a free account.
A free account preserves the short preview. Upgrade to Pro for the full transcript and episode chat.