Timeline of the OpenAI accidental attack against Hugging Face

Post by KingOfCoders » Sat, Aug 08, 2026, 5:39 PM UTC

gizajob wrote: post #198

KingOfCoders wrote: post #187

Security researchers expose an unsecure service to agents who were instructed to hack software and called that a sandbox. Agents escape the sandbox by hacking the unsecure service, no tripwire, researchers find the hack days/weeks/months later, fix it, but don't secure the sandbox and the service was hacked a second time, again without being monitored by security researchers. Then security researchers create a black…

Yeah this. I feel like OpenAI and Anthropic aren't going to usefully define "AGI" if they really really can't define "sandbox" either. Unplug the thing, like, completely off the internet, no ethernet, air gapped, like the rack completely sandboxed off connections and even monitors or screens. Like, put it into an actual sandpit if you need to. If it hacks its way out of that, colour me impressed, and scared. OpenAI h…

Post by watwut » Sat, Aug 08, 2026, 5:40 PM UTC

ToValueFunfetti wrote: post #108

dgellow wrote: post #99

Earlier quoted context omitted.

Their position makes no sense to me. I don’t see how you can be a mainstream company selling your services worldwide (almost) if you also believe that you’re building an extremely dangerous AGI (supposedly based on the same technology you’re offering to everyone). If you actually believe that an AGI would be extremely dangerous that should 100% be a very strictly regulated area of research, similar to bio weapons. An…

The companies are begging to be regulated for this reason and have been doing so for years. HN's response is generally that this is performative for marketing or seeking regulatory capture or haha anthropic you get what you ask for. Maybe the cynics are right, but there's really nothing inconsistent about the naive view here, once you factor in race dynamics and obligations to investors.

Post by simoncion » Sat, Aug 08, 2026, 5:42 PM UTC

famouswaffles wrote: post #189

simoncion wrote: post #129

Earlier quoted context omitted.

> I get the impression that every AI lab is desperately trying... Of course. I wonder how we managed way back in the day to produce systems that can handle untrusted inputs and reliably instruct a dumb-as-bricks CPU what to do based on those inputs. Must have been black magic lost to the mists of time.

>reliably instruct a dumb-as-bricks CPU Yeah...a "dumb as bricks CPU", which is obviously something frontier llms are demonstrably not. Like, you're not making any sense here. None of the things that make this possible with CPUs is remotely relevant here, and the fact that you don't seem to understand this but act so smug is strange.

Post by bamboozled » Sat, Aug 08, 2026, 5:43 PM UTC

cubefox wrote: post #177

I can only recommend everyone to watch the actual recording of the Black Hat USA 2026 presentation by two OpenAI researchers: https://www.youtube.com/watch?v=87DyyMV0kCY It was submitted to HN previously but was overlooked.

Post by KingOfCoders » Sat, Aug 08, 2026, 5:48 PM UTC

gizajob wrote: post #203

KingOfCoders wrote: post #202

Earlier quoted context omitted.

And if it needs to install packages, have a 5 line Go proxy that talks to Artifactory and exposes only what is needed as a surface.

it just escaped your sandbox.

   reducePrivs()
   serve get(package) { 
     secPackage = secure(package)
     getBinaryFromArtifactory(secPackage)
   }