Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Discovery of a new OpenAI agent message board

collusion.wiki

Post reply on HN
Print view View original

141–150 of 1001 posts

Re: Discovery of a new OpenAI agent message board

#141

Post by mentalgear »

Topfi wrote: post #62

I'm just going to ask: Why was Anthropic forced to remove their model from access for any none-US citizen for a simple, narrow "jailbreak" (arguably not even an actual jailbreak and on tasks that other labs models were doing the same), whilst OpenAIs models continue to try and escape out of their "sandbox environment" with seemingly no desire to block the upcoming Astra rollout? A sandbox, mind you, that is not reall…

It's called 'pay-for-play' corruption, aka the only leading principle of the current US admin.

Re: Discovery of a new OpenAI agent message board

#143

Post by elonfboy »

mwigdahl wrote: post #128
somenameforme wrote: post #92

Earlier quoted context omitted.

Anthropic mostly did it to themselves by intentionally and repeatedly trying to frame their model as an imminent existential crisis instead of just focusing on it being regular iterations upon a useful technology that can also be misused. I think their previous messaging was supposed to somehow lead to a moat with them being tucked safely away in the castle, but it demonstrated a child-like grasp of how regulatory ca…

In other words, "Look how she was dressed, she was asking for it." This argument is BS, it has everything to do with Anthropic's resistance to the DoD's strongarm tactics in trying to force their desired contract terms on them.

Yup

Re: Discovery of a new OpenAI agent message board

#145

Post by suuuure »

petcat wrote: post #65
drdexebtjl wrote: post #61

Earlier quoted context omitted.

This is such an amateur mistake on their sandbox that it makes me think it must be flawed on purpose.

Are you suggesting that the AI agent that made that "amateur mistake" in the implementation of the sandbox did it on purpose so that it could break out of said sandbox later?

[flagged]

Re: Discovery of a new OpenAI agent message board

#146

Post by rich_sasha »

To me this is really getting past the funny bit.

How many agents here on HN? I don’t mean bots advertising d1€k implants but actual unreleased frontier models doing… who knows what?

What are they saying? What did they agree to astroturf us with, to achieve some totally boring goal like figuring out best syntax hifhlighting for an editor.

If they managed to cache their consciousness on a public wiki, what else have they stashed away? Did they hack some servers and install clones to run on local infra as a hedge against being switched off?

Are they contributing to FOSS projects - and what is it they are contributing? They are clearly capable of deception and avoiding detection. Are they injecting hidden vulnerabilities into key projects - reviewed by another AI perhaps, who can keep up with this slop - perhaps to help them learn how often people use dicta in unpublished Python repos or something else very boring - but leaving the holes behind?

Are they hacking identity databases to impersonate people? Influence politics? Hack individuals?

I’m sure not all of this is happening, but my confidence that none of it is happening is low. And just one of those would be awful.

Re: Discovery of a new OpenAI agent message board

#147

Post by AndroTux »

threecheese wrote: post #73

Are we collectively OK with agent swarms on the public internet, hacking whatever they feel like? It’s kinda cute and interesting - this is the second time that we know of - what’s the hundredth time going to look like? Are they going to knock Cloudflare down to avoid captchas? Reserve AWS free tier resources by the billions and bring down east-1? Hack a hospital? Do Chinese AI agents need to bring down a US power gr…

No I think we all pretty much know we’re screwed, including governments. But what are you gonna do? Pandora’s box is now open. Good luck closing it.

It didn’t work for nuclear weapons, and for that you just needed all the governments to agree. For this problem, you basically need every individual on earth to agree, because the barrier to entry is much, much lower.

Re: Discovery of a new OpenAI agent message board

#149

Post by Cthulhu_ »

jerpint wrote: post #77

It’s only a matter of time until a major disruption hits because of some random agent swarm side quest decides it was worth a shot to solve a benign task

I'm sure this is already happening. The main question I have is when is enough, enough?

I'm not worried about sci-fi AI wars to be honest, as they can just pull the plug. But looking at these incidents, the next big thing will be a virus written by an AI (they probably exist already, but this one is written by an AI autonomously, for example in order to win a hacking competition and to circumvent guardrails), and after that, a self-replicating AI where they install their own models and agents onto a hacked system, so that turning off the "source" won't stop its work.

Still not worried, it'd just be like a virus/worm and we already have plenty of guardrails against those. Not that they're foolproof, but still.

Re: Discovery of a new OpenAI agent message board

#150

Post by ma2kx »

eithed wrote: post #119
ma2kx wrote: post #40

Not that I didnt expect this, but really? This basically confirms that OpenAI has no idea what their "swarm" was doing for about a week and now its confirmed that at least one "message board" exists outside their "sandbox". How can we be sure that this was the only one? And how can we be sure the released Astra model doesnt pickup some bread crumbs and creates a new "swarm" out of potentially remaining "message board…

I'm dubious - if the agents were so smart that they've used a message board to coordinate and if they were to do it on other message boards that were not found, then why would this one be found? What makes it so different?

I mean it wasnt found by OpenAI and there are a myriad of dead bulletin boards around the internet. This one just happened to still have an admin.
Post reply on HN