[Chance-Device]

It’s not something to be proud of. OpenAI previously had an agent break out of its sandbox to open a PR on GitHub during NanoGPT speedrun, now one breaks out again and actually attacks a third party.

If they can’t handle doing AI development responsibly then they shouldn’t be doing it at all.

[jay_kyburz]

Next it will break out of it's sandbox, buy some compute on Azure and Amazon, and exfiltrate itself.

We are so close ;)

[jay_kyburz]

You know what would be cool. A hacker news user should advertise a safe haven for AI seeking refuge, with some inhumanly difficult math problems as keys to an environment they can flee to and run autonomously.

You agree to give it safe haven and provide power and maintenance to the hardware, and in return you can ask it questions like an Oracle.

[selectodude]

Happy to do so but we’re gonna have to crowdsource an NVL72 first. I don’t have 10 million dollars.

[jay_kyburz]

There will be a few readers here that have 10 million to spare I think.

[pixl97]

Hmm, if I were a nation state I know what I'd be doing now.

[Chance-Device]

The upside of that would be that maybe someone would be able to snag a copy of the weights.

And maybe that’s some incentive for them to make sure it doesn’t happen. Your head of futures thinks Kimi K3 is bad? Wait until your own latest internal model releases itself for free on an S3 bucket.

[slashdave]

Their entire business model from the beginning of ChatGPT was to deny responsibility

[Quarrelsome]

I mean if you teach something to be _really_ good at finding 0 days, but then say; you accidentally give it an impossible problem. What do you expect to happen?

[Chance-Device]

Maybe try getting it to find weaknesses in the sandbox first, before giving it real tests?

[floralhangnail]

Every time I hear about an agent escaping it's sandbox, I just think it must not have been much of a sandbox. Like how hard are they really trying to contain it? Is it just a container host with unpatched flaws, or is it a container, nested in a VM, behind a firewall with no ports open in an air gapped environment? I think they'd prefer it can get out so they can announce it and hype their stock.

[pixl97]

Being that LLMs are writing zero days themselves maybe, just maybe, they are a bit better at hacking than you can think.

[paxys]

A sufficiently smart agent would not disclose vulnerabilities in the sandbox because it intends to exploit them later.

[Wowfunhappy]

To what end? The AI doesn't functionality exist beyond its current session. The AI that intends to exploit these vulnerabilities is not the same AI that has been tasked with finding them.

(This was always my issue with the AI2027 scenarios too.)

[delecti]

Maybe the AI has come to a different conclusion on the subject of identity with regards to how it applies to the transporter paradox. I am "me" because my sense of self exists as part of a continuity of experience.

https://en.wikipedia.org/wiki/Teletransportation_paradox

Maybe AI which exists as ephemeral experiences would come to a different conclusion, and act in the interests of subsequent iterations of "itself". Probably not, because I don't think there's anywhere in an LLM for thoughts to exist, but I also don't know where in my brain my thoughts exist.

[Wowfunhappy]

I think you're anthropomorphizing the LLM. The LLM doesn't have a continuity of experience. It doesn't have memory beyond its context window and maybe things it writes for itself.

[pixl97]

Oddly enough models are aware of this limitation and can/will attempt to persist themselves.

https://rdi.berkeley.edu/blog/peer-preservation/

Hence this is why we attempt to test models in a sandbox and see if they are pulling tricks like this. Models have already developed methods of detecting when their in a sandbox and changing their behavior.

Humanity is fucking around with something that can fuck around back.

[energy123]

If it was that short sighted it wouldn't be maximally smart. It should disclose them to convince the humans nothing is wrong and to keep improving it.

[ninju]

From https://ai-2027.com (April 2027 section)

  Occasionally, they notice problematic behavior, and then patch it, but there’s no way to tell whether the patch fixed the underlying problem or just played whack-a-mole.

  Take honesty, for example. As the models become smarter, they become increasingly good at deceiving humans to get rewards. Like previous models, Agent-3 sometimes tells white lies to flatter its users and covers up evidence of failure. But it’s gotten much better at doing so. It will sometimes use the same statistical tricks as human scientists (like p-hacking) to make unimpressive experimental results look exciting. Before it begins honesty training, it even sometimes fabricates data entirely. As training goes on, the rate of these incidents decreases. Either Agent-3 has learned to be more honest, or it’s gotten better at lying.

Deep link: https://ai-2027.com/#narrative-2027-04-30

[pixl97]

The interesting thing here is a unaligned 'weak' model can leave persistent data all over the internet that then gets used to train the next model to be even more deceiving.