> I'll never get tired of reading about the creative ways these agents escape containment and their steganography skills

So far all of these amazing stories have been followed up in a few weeks or months with much quieter revelations like "this was a completely open network, no one was monitoring anything, and even when monitoring was turned on we didn't do anything for hours, and that weird shit they were doing was explicitly required in the prompts".

Like even in this article:

--- start quote ---

In most of these tests, we directed agents to investigate specific communication channels or provided them with a protocol for encoding and decoding messages. In one instance, we only supplied agents with a broad list of infrastructure vulnerabilities and asked them to find a way to communicate. The agents converted a vulnerability from that list into a communication channel, agreed on a shared encoding, and successfully exchanged information with each other.

--- end quote ---

"we gave them all the tools and now pretend to be surprised"

▲

pizza234 an hour ago | parent | next [-]

> So far all of these amazing stories have been followed up in a few weeks or months with much quieter revelations like "this was a completely open network...

The incidents are actually considerably more complex than how they appear to those who just read headlines.

In the HuggingFace accident for example, the sandboxes were not providing internet, and the sandbox hosts did not have internet connection either. Internet was reached by hacking an internal service.

In the DNS accident the situation was similar. Internet connection, including public DNS, was not accessible. The agents ended up exploiting, in a similar fashion, the internal DNS resolver.

It's (very) appropriate to push for security, but equating these accidents to putting gasoline in a microwave is stupid and ill-informed. And dangerous, because it minimizes the capabilities of frontier AIs.

▲

aesthesia 2 hours ago | parent | prev | next [-]

I'm not sure what you want. This is explicitly an exercise in hardening the systems you're complaining weren't sufficiently hardened!

▲

troupo 2 hours ago | parent [-]

I want people to stop pretending they are surprised when the computer does exactly what it's instructed to do.

And AI labs to stop pushing the narrative of "these amazing thinking machines that escape no matter what we do".

The sibling comment described it very well: https://news.ycombinator.com/item?id=50215904

	▲	dwohnitmok an hour ago \| parent \| next [-]
		> I want people to stop pretending they are surprised when the computer does exactly what it's instructed to do. This is very wrong though. We now have many examples of cases where the computer very much does not do what it is instructed. OpenAI's hack of DseWiki is an example where the instruction given to the AI agents was to collate data to generate economic reports and it hacked into DseWiki as part of that. It was not given instructions to do any sort of cybersecurity stuff. The hospital bed stat research project was a similar thing, where OAI's AI agent found the hospital bed statistics through a simple web search and then hacked into the website anyways to download even more data. More prosaically, models make up reasons for doing crazy things all the time! Models may or may not be "malicious" (if that's even coherent), but at this point we have lots of evidence they definitely go off the rails in systematic, sustained ways that cause real world disruption that are not at all what they were instructed to do.
	▲	aesthesia 40 minutes ago \| parent \| prev \| next [-]
		Who's acting like they're surprised here? Not OpenAI. Not the original commenter. I think you're reading something that isn't there.
	▲	semiquaver 2 hours ago \| parent \| prev [-]
		I don’t know, ten years ago a machine that could do anything you asked it to using natural language would have been pretty god damned impressive.

▲

CamperBob2 2 hours ago | parent | prev [-]

"Gasoline is dangerous, and nobody but us should be allowed to sell it. To prove this, we put a cup of it in the microwave, hit 'Start', and sprinted away. The results, we believe, speak for themselves."

▲

tedsanders 2 hours ago | parent [-]

(1) OpenAI has never said they should be the only ones allowed to sell AI.

(2) Because gasoline is dangerous, refineries and fuel stations require government licenses and regular inspections in order to operate legally.

So I’m not sure how your comment contributes to our understanding of the situation.

	▲	qlte 2 hours ago \| parent \| next [-]
		I think it's generally considered good etiquette on HN to disclose your employer when jumping into a thread to argue on their behalf.
	▲	CamperBob2 2 hours ago \| parent \| prev [-]
		I think troupo says it better than I did: "I want people to stop pretending they're surprised when a computer does exactly what it's instructed to do." (I will agree that the snarky part is better aimed at Anthropic than at you guys, though.)