Viewing profile — KingOfCoders

"and it gave them a false sense of security." This was part of evaluating cyber security of their frontier models and they had a "sandbox" which, and I'm not a security researcher,…

How is that possible if the OS/drive/vault is backdoored? Could you elaborate? I think "resilient" just means "backup copy" and I do think (IANAL) it is illegal to destroy emails w…

"They don't need Internet to give their agents access to tons of software." I think that was the requirement, but yes, the cache could have been offline. Still then they could have…

We offer EU data centers for customers that want their emails to stay in the EU but "Resilient replicas of your data will live in the US" ?

How can it escape an "install package " proxy? reducePrivs() serve get(package) { secPackage = secure(package) getBinaryFromArtifactory(secPackage) } I would think the code is very…

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.

An agent idling and then acting on it's own to hack HF is has nothing to do with guard rails. Someone had to give the agent some instructions, like "hack X", "Find exploit for Y" o…

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,…

I now watched the video. It seems the agents were sharing context for months, run unattended for months, the sandbox was no sandbox at all, one agent hacked a service and announced…

Cui bono?

Why scared? "Our agents have super intelligence and can hack everything on their own without direction" increases the IPO value and doesn't decrease it.

[edit] I've now watched the video on the idea that your write-up was misleading. BUT the video is much worse. For two months with highly dangerous agents agents were hacking a serv…

It does not explain how agents months later would "collaborate" to hack Hugging Face.

I think for the power you have and how many people listen to you, you should have added context. All of it is made as if without prompt or direction, agents on their own initiative…

Reminds me of The Last Unicorn, the wizard also tells magic "to do what it wants"

No because he doesn't ask the right - and to me, subjectively, obvious - questions.

My read is: One did it as a PR stunt, the others saw that every media reported on this and did the same.

Had a high opinion on Simon Willison, this broke it.

"The agents found a Modal-hosted insecure app with a weak API key, then used that to stage an attack against Hugging Face." Why, what was the prompt? I told Claude today to wire pl…

Show me the prompts or it didn't happen.

"More agents discover this new informal message board while browsing Artifactory’s file listings, and start reading and writing messages." Yeah, my agents also discover what other …

All of that is plain PR.

" bypassing security" If they can bypass it there is no security and the security was flawed all along.

Doesn't the picture I "see" depend on how close I get to the "frame"? Does the camera take this into account when making a photo?

"That is only your own interpretation." There are many people on the internet who think their interpretation of things i the only right one. Don't argue.