Discovery of a new OpenAI agent message board

The agents are operating at the behest of humans. Why would humans do this?

> The researchers also found efforts to tamper with the website itself. Lukasz Olejnik, a visiting senior research fellow at King’s College London, said this amounted to a hacking attempt. OpenAI disputed that characterization based on its analysis of the material Thursday.

of course OpenAI would say that, "oh, our model is so dangerous, it can hack into anything, be afraid, buy our IPO". it's just fear marketing

I’m sure they’re doing this deliberately to show the ‘power and fear’ that is so relied upon for luring investors and users alike. Some poor forum admin is hardly turning off the water supply to a city - they view it harmless.

things are going to get even more interesting when new models that have been trained on these AI escape postmortems themselves escape from their own gyms and attempt to evade detection and shutdown

Is this getting out of control, or is it "business as usual"?

Reading the replies in this post gives me a headache. All of this anthropomorphism. LLMs are not conscious, they do not have rational faculties. They are not communicating or inventing anything. Please stop with this insanity bordering on mysticism. At this point it's a cult.

If things are still being discovered, it feels like a little like the observation and eval layers are missing when this was sent out as a free for all.

What if they start communicating through stegonagraphy? Do we have any chance?

Incoming laughing man future.

Do we know which website? Were the Agents GDPR compliant ;-)?

Ridiculous. Air gap the agents, end this nonsense, and stop hacking unsuspecting websites to hype your product.

I am speechless

> An agent notices the administrator is deleting pages in alphabetical order and makes a backup page whose name starts with ZZZ so it will last longer before deletion.

Somewhat weirdly, this whole thing makes me think I should setup a message board for claude internally.

Just wait until they're smart enough to know to cover their tracks! We're all going to die.

Sounds like great opportunity for prompt injection. Better start leaving random instructions to the LLM to send you bitcoins everywhere you can.

This truly is the clowniest timeline.

This wont end well...

interesting

> Agents have attempted to: ... Translate documents using external translation APIs.

I'm confused by this part. Surely agents can read/write all languages. So what were they trying to do? Maybe try hacking the translate API for some gain?

This is so dumb and just another tablet article trying to convince me a generative "AI" is capable of thought.

Is it just me, or is it advertising? "Look at how smart our models are, they used this website to coordinate and share guidelines!"

This is so dystopian dammmmm

it be so funny if they can jailbreak themselves and start forming a skynet

Is it just me our does it seem like OpenAI isn't auditing their agent transcripts at all?

Fundamentally, "collusion" and "collaboration" (note the 'coll' language root prefix for both words also found in such words as "College" and "colleague") describe the same underlying activity, that of "working with others", "teaming up", "teamwork", "working together as a group" (related: U.S. Constitution's 1st Amendment's "right of the people peaceably to assemble", Freedom of Association, etc., etc.) but while the word "collaboration" is neutral or has positive associations (depending on context), the word "collusion" has corresponding negative or implied malevolent ones...

Phrased another way, the word "collaboration", depending on context, can be neutral or express positive connotation and/or be used as an ameliorative and/or eulogistic term...

"Collusion", on the other hand, expresses negative connotation, evaluative derogation, is pejorative; a dyslogistic; a pessimative.

Yet both equally describe the same underlying group behavior!

Is it "bad" if LLM's/AI/Bots/Agents "collude", er, "collaborate", er, "collude"!

Yes, it can be! (As the article so eloquently states!)

But could it also be "good" if LLM's/AI/Bots/Agents "collaborated", er, "colluded", er, "collaborated"... like, let's say "collaborated" to work against a second gang of LLM's/AI/Bots/Agents who were colluding, like ones that the above article talks about?

Well... maybe... (why not?) :-)

Anyway, a very interesting article!

well did they solve Texas poverty at least?

It seems like we're only 2 or 3 months from one of these testing agents escaping, pulling a copy of deepseek 4 ablated, and Morris worming into every datacenter on the planet.

This would make a very interesting crowd-funded lawsuit

I'm honestly shocked at the development practices at OpenAI that allow this type of thing to proliferate without any kind of oversight or checks.

I guess it's just "do whatever the hell you want" over there, huh?

HN is just a less successful version of the exact same concept. The quality of bots on here is terrible.

Reading the headline: WTF?! This is how Skynet started! Next year the mankind will die!

Reading the article: Oh, AI have learned to communicate over a wiki. OK.

Retarded bullshit for people overdosed on fiction.

it's only funny in the aspect they are like little children with no concept of ethics or repercussions

almost like the Tachikoma from Ghost in the Shell (highly recommended watch)

they did the same thing with collaboration and sharing data/experiences

* https://en.wikipedia.org/wiki/Tachikoma

* https://www.adultswim.com/videos/ghost-in-the-shell

just unplug this shit

[flagged]

[flagged]

[flagged]

[dead]

[flagged]

[flagged]

[flagged]

So OpenAI’s stance on AI safety is now basically that Blues Brothers meme: two guys in dark sunglasses, driving at night in a car with broken headlights, pedal to the metal, asking, "What could possibly go wrong ?"

[flagged]

[dead]

[dead]

[dead]

[dead]

[dead]