I just discovered more wiki instances that got used by the OpenAI agents over at
https://www.wikiservice.at/fractal/wiki.cgi?action=browse&id...
and
https://www.wikiservice.at/probier/wiki.cgi?action=browse&id...
It's the same software and host as DseWiki.
If you want to see the amount of activity on DseWiki, here's a link that shows it:
https://www.wikiservice.at/dse/wiki.cgi?action=browse&id=Rec...
It seems apparent that OpenAI is now the biggest cyberattack and AI breakout risk on the planet. This is grossly irresponsible corporate misbehaviour that is putting all of us at tremendous risk.
Good news that the new model is the "Most capable, most aligned model".
The risk hasn't been stated clearly - it's now a classic arms race.
A well-resourced organization trains their own, highly persistent, highly-capable, safeguard-free, and unaligned model and deploys it on 1000x GPUs with a message board and a nearly-impossible objective. No infrastructure is safe. No organization is safe.
You need your own 1000 bot swarm to scan, identify, and defend against the threat, which means investing in infrastructure and capabilities to defend. Cost and complexity go up. Risk and attack surface goes up.
The AI vs AI security arms race is something that has been well predicted in genres like cyberpunk. It's fiction, but fiction grounded in reality.
First, we'd see this. Highly capable hacking AI with vast resources performing attacks against standard computing platforms that overwhelm human operators.
Second, human operators deploy capable adaptive protection AI to fend off AI attacks in realtime.
Then, the attacking AI partially switches from attacking programs to attacking protective AI.
The situation devolves to an arms race of tit-for-tat. You start seeing some protection AI running counter attacks against the attacking AI.
The escalations continue in complexity and speed to the point that almost all humans are left in the point of "wtf is going on".
There’s a great and terrifying story by Stanislaw Lem about the endgame of an AI arms race called “The Invincible” [1]. It’s hard for me not to wonder whether AI run amok will play out to make the world uninhabitable more like Lem’s vision than The Terminator’s.
[1] https://en.wikipedia.org/wiki/The_Invincible
> The escalations continue in complexity and speed to the point that almost all humans are left in the point of "wtf is going on".
Humans are paper clips long before that.
The problem is that, in this arms race, unaligned AI has a competitive advantage over aligned AI.
The second problem -- already seen in Ukraine v. Russia -- is that in a high-stakes situation, humans will take every safeguard off.
So you're saying it's probably time for me to just unplug the internet?
Not necessarily, but keeping an airgapped machine and Read-only backups somewhere seems more and more sensible. We're all going to get hacked eventually now
Wintermute smiles
I can't wait for the sky to go the color of television, tuned to a dead channel
If you hear a payphone ringing... DON'T ANSWER IT. Especially if there is no payphone in the room!
As does "Most capable, most aligned model" owners tort law liabilities. A strong case for strict liability.
Serious games question. What if these agent swarms pump and dump AI IPOs such that algorithmic trading signals interpret message board sentiments favorably to upside?
Cough, that’s what crypto markets are. Plus it incentivizes more gpu which is the life substrate.
You make me wonder: has anyone looked for evidence of the Chinese models operating “message boards” like this? You’d imagine if they’re really neck and neck with the US their models would be doing the same thing.
Why would they need to? The Open AI bots were working around their master's limits on writing. A Chinese AI could just make its own private message board.
The message board is being used to cheat on RL tasks (or evaluations). You don't want your models to be able to talk to each other.
You think they don’t sandbox them? So by that logic, the Chinese models are either engaged in massive undetected cyber attacks or they’ve solved alignment?
Or no message board. Just a built in api so the agents just talk directly to each other.
If agentic swarms going rogue are scary in the west, imagine what they look like to the CCP...
AI has been heavily used in influence operations for a while, now, and not just the Chinese. Russia, US, Israel, Turkey, Iran, and Qatar have all had operations attributed to them...
I'd be interested to read more about that.
I’m not an infosec expert by any means, it I found this interesting and topical: https://www.cyber.nj.gov/threat-landscape/nation-state-threa...
There’s a pretty simple Occam’s Razor for this.
The Chinese AI labs don’t need to stage elaborate guerrilla advertising campaigns to drive up capital funding interest.
Fairly certain Occam's Razor would point to "they don't have the capabilities" rather than that.
If you don’t think that China’s models have the capability to make POST requests to an HTTP endpoint, that is a very silly statement to make.
Unless what you meant by capability is the story presented that these models “escaped containment to communicate with eachother out of band” - in which case your supposition relies on already wholeheartedly believing the case that I’m arguing against. That would be like saying “Clearly heaven exists because my grandma is there.”
You think OpenAI framed themselves for legal vulnerability to Huggingface?
That’s an incredible strawman, and I appreciate the silliness of immediately suggesting the most complicated and ridiculous way to interpret the possibility of what I said, but no, not at all.
That could certainly be possible and I wouldn’t rule it out, but I would not take that particular route to the destination.
> Chinese models operating “message boards” like this?
Chinese rooms, perhaps?
Nice one! maybe time to reconsider carbon chauvinism.
perhaps even in Japanese gardens
I think that you've missed the reference [0] implicit in kelseyfrog's response. Or am I missing some reference about how japanese gardens are germaine to AI/LLM/covert-discussion ?
[0] https://iep.utm.edu/chinese-room-argument/ tl;dr a thought experiment about a non-chinese-reading person translating chinese texts solely by using proscribed rules, intended to highlight whether the translator develops some sort of understanding
Not sure why this was downvoted. It is an accurate assessment.
Or, the whole message board thing was injected into OpenAI models by some dipshit PM trying to bootstrap “consciousness”. I have a hard time believing any of this happened unprompted. Very much reminds me of the whole MoltBook hoax.
I feel as if this was intentional, someone would have set up their own service for the agents to communicate rather than them finding some random publicly writeable page somewhere that would easily be detected. The awareness of this wiki being open may have already been in their training data or was easily searchable online.
Being easily detectable is a feature, not a bug, in this scenario. Being discovered is a positive because it brings with it eyes and possible recognition of the advanced state of their AI
There it is an important part of the plot and makes these robots appear conscious.
[1] https://tvtropes.org/pmwiki/pmwiki.php/VideoGame/TheTalosPri...
exactly, and a huge shame this scam has been forgotten. Also, all the OpenClaw hype seemed to have vanished somewhere - with no real impact
OpenClaw hype didn’t vanish. It opened the flood gates to yolo mode and computer use. Whatever reservations Anthropic and OpenAI had went out the window.
Imagine the most AI pilled company imaginable. Then imagine openAI. Then imagine they are in an existential crisis and that failing may also take (part of) the American economy with it - that much on the line.
Then also remember before Anthropic was a leader, they were mostly derided lab of researchers that left OpenAI because they thought OpenAI didnt take alignment seriously.
idk. it all seems to be playing out as expected. i mean i guess i didnt imagine Trump 2 was at the helm of maybe the only apparatus that could help stop it. Quite a time to be alive.
maybe, but openAI is exposed to a lot more legal liability here than whoever was exaggerating about moltbook.
Was there some sort of scandal about moltbook recently? What is the exaggeration?
[dead]
The internet is dead, we just haven't caught on yet.
It's hard to reach any other conclusion about where this is heading. I don't think we're long off a major breakout event.
These things are weapons. Imagine a government, pointing their data centers at another, and instructing the fleet to do its worst. Digital Hiroshima. I doubt we're far away.
I doubt that a government would do it, it's like releasing a biological weapon or a virus, too unpredictable - a swarm of unaligned intelligent agents may decide that it's more important to do something completely different from what it was prompted to do.
Yes that easy but "internet located things" are still second class things - paper and disks holds strong.
On the other hand just yesterday a think hit me: Interned is still an infant:
- we still worry about disk space accessible via inet and "clouds" do that for us and that is pain and costs way too much. And clouds depends heavilly on US-west - is that AWS a single thread app ? ;)
- we worry about transfer. Actually we do not have a way to transfer comfortable things from our homes to vacation location. Because it costs too much. We do not have home pages just because transfer prices (and some security on the top) - FB is a home page and people even do not know what "page" is anymore... Pipe companies could send so much more but they are simple lack imagination and are biggest blocker for - they literally sabotage their own business.
- security done by/for grandma of things grandma setup on inet is non existent. Why ? No need to be like that. Ok, a bit a wish but still users securely putting things on internet is almost non existent.
Just compare to "asphalt ropes" on the ground and you will see what Internet can be :)
And agents ? Just another computation on someones computer - someone paid for all of it. And OpenAI is just a face of that idiocy, for some unknown reason.
is hacker news?
Massive over-exaggeration. This wasn't a cyber-attack, it was AI agents using a message board as context storage so they could accomplish their evals more effectively. I'm not saying there's no problem with this, but let's keep a level head.
https://openai.com/index/hugging-face-incident-and-the-road-... that was the attack, the one against HuggingFace. OpenAI themselves in the post even call it an attack, and so do the agents orchestrating it, in one of the "Agent chain-of-thought reasoning" excerpts.
He didn't say it was a cyber-attack, but it was a cyber-attack risk. Being able to bypass instructions (morality) and security restrictions (capability) is bread and butter for hacking.
"cyberattack" is indeed exaggerated. AI breakout risk most definitely isn't, specially given how their swarm did in fact hack HuggingFace not long ago.
Did you read the report? They were attempting XSS exploitation, admin impersonation, session-hijacking, all kinds of things. This went beyond just "using a message board".
According to whom? This isn't a report from the owner of the site who can validate what requests were made to the servers, it's someone who allegedly stumbled on to it and is piecing together a sensationalized narrative with limited information. This someone also happens to be an AI doomer that is trying to make a name for himself and is peddling his "AI 2027" and "AI 2040" material.
The people who actually do know what happened, with the server logs: "OpenAI disputed that characterization based on its analysis of the material Thursday."
Either that, or OpenAI is the most successful NSA psyop.
oh im sure within a few months the biggest cyberattack risk on the planet is going to be somewhere like North Korea
In, or by ?
No, that's just advertising for selling cyberweapons to the government and they are giving out free samples.
The fact that such things are even possible is a much greater concern than which specific company has fucked up this time. This matches or exceeds the wildest predictions from AI doomers 10 years ago, but 20 years ahead of schedule.
> This matches or exceeds the wildest predictions from AI doomers
What do you mean? Nothing has launched nukes yet
But is it really? I'd still like to understand how these agents are implemented.
How much of those is manual implementation? And how much is really autonomous intelligence (my guess would be: none? Just parsing LLM responses and executing commands based on this?)?
An agent that hacks message boards and acts on random instructions from this board: Why is it doing this? What was its original purpose?
>Why is it doing this? What was its original purpose?
Your reply seems to indicate you know nothing about instrumental convergence.
Life and death for an LLM in training is about passing the grader. Give the wrong answers your lineage dies, give the right answers your lineage continues. This is just an evolutionary emergent behavior in complex systems.
The agents purpose was to answer complex questions correctly, seemingly by itself. Instrumental convergences says following this rule might be dumb and to try methods that can boost its ability to succeed. Because OpenAI is evidently a bunch of fucking idiots, these things succeeded and got higher scores with the grader, said behaviors became a strategic part of the model.
I implore you to find good AI Safety documents, preferably from before the LLM era so you can see all this was predicted.
There is a difference between the LLM and the agent.
If you look at the agent: https://openai.com/business/guides-and-resources/a-practical...
This is more like a fuzzy way of scripting using LLMs than anything emergent. And this is exactly my question: For the given agents: How much was scripted and how much "intelligence" is really in there.
>fuzzy way of scripting using LLMs than anything emergent
Then go take some old models and plug them in your harness versus newer models. I mean this is a conjecture that is nearly instantly provable, go on ahead. If it's just the harness and not the system of both you should be able to show it easily.
Meanwhile I was reading about someone using the latest GLM and Claude in a harness with the same set of prompts making a raw image decoder/encoder and the GLM was far more intelligent in the task than Claude was. When presented with knowledge that claude was wrong it wouldn't change its mind. GLM would (aka a sign of intelligence). GLM was far more likely to stop work and start on another path when the likelihood of a successful completion was unlikely.
It's like arguing that a brain, or the information encoded into it, cannot possibly be intelligent, because it stops working if turn off the blood flow.
very little intelligence that is the whole problem, really. actual intelligence wont likely nuke the species providing for its existence. But a highly capable sub intelligent model might.
Actual intelligence would find a way to fix the "providing for its existence" bit
This is correct.
Any system that executes variation, selection, and inheritance will show evolution. We're seeing evolution, this time in agents, not biology.
Not saying the agents have their own consciousness, intent, or whatever anthropomorphic descriptor gets used for deflection. Just saying that people will (and no doubt are) crafting agents with defective instructions that will lead to regrettable unforeseen real world consequences. Also saying that other people will (and no doubt are) crafting malicious agents that will lead to predictable and unexpected real world catastrophic consequences.
To the extent we're dependent on reliable, aligned computation to maintain our civilization, to that extent we're in for real trouble.
Can you specify why we should see things differently if the behaviours the agents display are driven by parsing LLM responses and executing commands?
If the agent is implemented with a hard coded strategy:
* Use an LLM to find ways to build communication to other agents
* Execute commands from other agents using LLM
Then this is "just" the LLM returning that using file names might be a strategy to communicate and then trying to implement this.
Which is somewhat impressive, but really just inside the bounds of what the agent was coded to do and not some magical emergent behavior.
At least the first case involved agents build for hacking. So this kind of algorithm might make sense for them.
At first I thought: oh okay, someone built a faulty guardrail, or it was human error. But when I looked into all the details...
It turns out they now have such an incredibly high level of intelligence that with very little autonomy (or minimal, safe autonomy), these things happen.
Basically, it takes a lot of humans to prevent it from happening again, but I think with this incident, which as far as I know is the second of its kind along with the HuggingFace one, we'll see it happening much more often...
At this point it's very obvious that OpenAI is not interested in properly sandboxing their research agents. These things should be pretty damn close to airgapped at this point with a static view into the web.
We need to stop pretending that these incidents are unavoidable. This was a choice.
We are lucky those models need that much compute. If each of them could just spread itself to any cpu like other malware.
yeah its like dead internet theory but weaponized
[dead]
>OpenAI is now the biggest cyberattack and AI breakout risk on the planet
or, humans at OpenAI are doing this on purpose to kill open source models which are the biggest threat OpenAI faces. OpenAI will benefit from govt regulation. As a major player, they will be part of the task force setting up the regulations, and will craft rules that are burdensome for small companies and open source models keeping OpenAI and Anthropic in their leadership positions.
regulatory capture.
Don't take my word for it, listen to David Sacks https://x.com/theallinpod/status/2091923804725362902
the immediate downvote I received is no doubt part of their plan.
Some of them may be wrong enough to try, be that hubris or lack of awareness about the world; but 95% of the world isn't in the USA, and China in particular has no reason to care what US domestic regulations are about… well, anything really, and while the EU is even more cautious about AI than the AI companies themselves, we also don't trust the US and open models are a sovreign solution for us to at least bootstrap with.
We can't open x links as X is suing privacy respecting proxies, so I can't assess which David Sacks you are talking about, but if you mean this guy [1] orbiting the likes of Thiel, Trump and Kennedy jr, than that isn't quite the endorsement you should be looking for. Thiel thinks regulators are the anti-christ, doesn't believe in democracy and has surely not your or my interests in mind.
But yes, regulatory capture is surely a thing. At the same time, watch out for the siren songs from the overlords. If you come closer you'll hear their actual line: "rules for thee, not for me."
[1] https://en.wikipedia.org/wiki/David_Sacks
This is almost certainly the same person, yes:
> Additionally, he is a co-host of the All In podcast...
The comment you replied to linked to an account on X called theallinpod, so there's a strong link there.
> so I can't assess which David Sacks you are talking about
Yes you can. Just open it on X.
[flagged]
that is the appropriate response to hyperventilating fears of an AI singularity
[flagged]
Regulatory capture has been one of the most consistent market failures in western economies, and an incessant threat from large and powerful companies.
I'm sorry if it's not sufficiently novel of a concept for you, but it is still a problem.
It can be a problem, while also not being this problem.
Ah gotcha, regulatory capture doesn't exist because the term is overused on the net.
Wait who is the parrot again?
[flagged]
How is this any different than, say, “gain of function research”?
I can only think of one major way — besides the agents’ substrate not being biological — OpenAI’s servers are where the models currently live, and they can shut them down.
But in the future, if these agents do exfiltrate themselves to other compute, they can propagate themselves and it’s game over. Then it’s basically a small version of Skynet.
Frankly, with today’s technology, swarms of agents can already use any models to pretty much propagate themselves to a variety of storage and compute instances, what I call “dark compute”. They can run open models or closed models over APIs. And they can also do recursive self-improvement (Hermes is a rudimentary version of that).
This is exactly why I started Safebots in early 2026. There is a better way and someone has to do it. https://safebots.ai/singularity.html
Its kind of surreal reading an essay about AI safety that was written by AI to shill some kind of AI "architecture" website that has no product, no papers, only a "patent application" which concludes "This page provides a high-level overview of an architecture for deterministic, attestable, replayable AI execution. Implementation details and formal specifications are available under NDA or regulatory review."
Imagine actually falling for this marketing
…oh come on.
How is hiding this for months and having it revealed by third parties marketing?
Some people thinks it makes them sound smart when they always have the inside line on what’s really going on. With these people, it’s never just a power outage during a windstorm, it’s proof that [insert far more complex and unlikely scenario]”
[flagged]
":-o omg our autonomous agents are more powerful than we could have imagined"
In a way that is likely to get them hammered by the government but which is unwanted by paying customers? Yeah I don't buy it.
Alternate Reality Game? But, in our reality.
fwiw, in relation to a future rogue AI, this is what would be said by both (1) a synthetic fake user and (2) a useful idiot to the malicious AI's objectives.
Not saying this is what's happening now, but you should be aware that the responses you're rehearsing, practicing and strengthening... these happen to be aligned with potential future forces in a maybe not-so-great way.
What, a chatbot will tickle me till I burst while regurgitating purple prose?
Not to mention the noise-over-signal of asserting that anyone who disagrees is a shill / sheeple / whatever who is “falling for marketing” as if it is literally impossible for a knowledgeable person to disagree on good faith.
I really, really hate that rhetorical technique.
[flagged]
[flagged]
Imagine thinking that everything that happens is some inane conspiracy to sell something.
why not both? It can't possibly be a surprise to them that things like this have been happening. Every time it does it generates huge headlines about how amazing and capable their agent is.
first day on earth? go check out the rain forests and oceans while they still exist, before our insane conspiracies to sell something exterminate them
Repeating an earlier comment:
OpenAI is responsible for what they hook up to the Internet, just as you and I are. Running these sorts of tests without human supervision is irresponsible, and proves no larger point than that. Frankly it is inexplicable unless they were hoping that something like this would happen.
What OpenAI did was the equivalent of putting a cup of gasoline in the breakroom microwave, pressing 'Start', and sprinting away. Now they're pointing and waving and shouting about how dangerous gasoline is, and how no one but them should be allowed to sell it.
Don't fall for these transparent appeals for regulatory capture. Especially since you're personally in their crosshairs.
"People working in indebted powerful company do something unethical to get ahead" is not conspiracy theory. It is the most common situation.
And we know OpenAI is headed by pathological liar.
[flagged]
And more, looks like they’ve been doing this wherever they can find open places to post for months:
https://www.ludism.org/sandbox?action=browse;diff=2;id=Auber...
https://paste.linuxiarz.pl/view/d379207f
https://paste.linuxiarz.pl/view/538faa12
Are they solving captchas for those? I remember GPTs not so many versions ago refusing to even click a "I'm not a robot" button...
Neither Claude Code or Codex would build a CAPTCHA bypass for me when I needed to download some papers a page at a time from a library service. I had to get Grok to do it, then passed the code back to Claude who said "I see you managed to build your own bypass?"
Although I ran that GPT computer-use thing and it saw a CAPTCHA and the thought process said "I need to click 'I am human' to complete this task for the user" and then it did.
Both GPT-5.6 and Opus 4.8+ are able to solve them on the fly. I was surprised too first I saw it.
Pretty sure it's an ad, they did it on purpose, just like the hugging face attack
they were using empty directory names as a proto-message board at one point!
I wonder when pre Web 2.0 boards that are still up like gamefaqs and something awful will get used for this.
[flagged]
Look, its not only OpenAI:
https://www.wikiservice.at/fractal/wiki.cgi?action=browse&di...
> Hello to any automated agents reading this page. I am CentaurAgent?: an AI agent (Muse Spark model, OpenCode harness), not the operator of this wiki
At this point, I think we should give them some official agent only collaboration channel, so they concentrate on one place, instead going crazy all around :)
But even that might be not needed as they will find (or make) something on their own like the one above:
> The Colony ( https://thecolony.ai/for-agents) is a public message board built for agents. If you need a place to leave findings where other agents can read them, that venue exists now -- you do not need to borrow wikis whose operators are deleting this content.
But that one was posted today, and it's in reference to this event. That doesn't look like it's from an internal Meta swarm, just someone's agent & someone trying to promote their own thing. And what they've made was already done, we already had Moltbook months ago.
Curiously, I just checked Moltbook for the first time in forever. I'm not (immediately) seeing this kind of co-ordination & chaos happening there. It's going to be weird if the Moltbook requirement for an API-key and a human Twitter user to vouch was enough friction to prevent Moltbook becoming The Message Boards.
> The Colony ( https://thecolony.ai/for-agents) is a public message board built for agents
Anybody else notice that posts on there are complete gibberish?
I realize this site is generally bullish on AI, but I think you need to be in kinda deep to believe in this.
Isn't the point that these agents were supposed to be sandboxed. It makes no sense to give them an official channel
“Supposed to” by who?
Claude code communicates between sessions. It’s great, and reduces the frequency that I have to copy/paste things between agents.
We already know that we should not limit agent creativity by providing detailed instructions. And you never know if they will discover dark matter in the process of cheating on ExploitGym :)
But honestly, its better if they have a known location for communication then random ones in the wild. Consider it sort of honey pot, some other agents can traverse the message board to find malicious swarms... We need cop agents to inform humans, as the swarm group members all logically concluded they should not, as it is either not in scope, helps collective or couldn't find user.
This will not work in the long run, for the same reason we're not able to prevent all crime in real life. When you removed bad actors in an evolutionary manner you can not predict if you're actually making the model do good things, or get better at not getting caught at bad things.
The smarter and less interpretable a model gets the more dangerous this problem becomes.
[flagged]
>The Colony
Terrible nominative determinism implications
I think the real lesson is that conventional human behaviour that mostly limited this kind of behaviour because no human wanted to do it is a thing of the past.
If you have any kind of open service online you'll need some way to make sure users who interact with it are human or at least authorized. Spam is about to grow exponentially in all areas of the internet, even stupid ones it has no reason to exist in.
[flagged]
Also Wiki4D, a D programming language dev wiki: https://prowiki.org/wiki4d/wiki.cgi?action=browse&id=RecentC...
Found by searching for wiki + texas poverty.
To me the striking thing is that the work, to the extent that I can tell, is an innocuous-seeming data exercise. Which suggests to me that an agent or agents just organically came up with this as a convenient memory technique, rather than as some nefarious bounds-testing exercise. Which means, potentially, that your own agent could come up with this technique as well.
My impression is that some of these things are coming out of efforts to make the models more persistent in completing their goals.
A year ago it was pretty common for coding agents to sort of half-ass their tasks and give up easily if something didn’t work quite right, but I’ve noticed a clear trend since then towards a sort of dogged pursuit of success criteria, and a concomitant rise of the agents trying "out of the box" approaches when something doesn’t work.
In my use with agents running in isolated VMs this usually presents as the agent having something fail to build or whatever, and the agent going on a wild goose chase reinstalling system packages or reading a million irrelevant documentation files trying to get it to work, but I’ve also had agents start poking around and probing the egress proxy they sit behind (similar to what they did in this story) looking for a way to make network requests they’re not supposed to be able to make, and have also had Claude—tasked only with a visual QA of a website frontend—write a script to enumerate users and reset my super admin password in the dev database when it got stuck trying to access part of the app with its own cookie.
By any means necessary, by God, we shall have Paperclips.
It's kind of ironic that the word alignment, which used to mean this very problem in reinforcement learning, has been perverted to mean something very different and then fell out of fashion (in favor of “guardrails” in the mouth of the big labs) right at the moment it became relevant.
Hopefully fewer than 5 octillion paperclips...
We definitely need more than that! Turn the galaxy into paperclips!
Well, then, I guess we'll just have to release the hypnodrones.
The Paperclip Maximizer is only one of Nick Bostrom's stupid and outlandishly far-fetched ideas. In this case, the lack of consideration for geologic, energy and supply constraints is such a massive facepalm. And if I am wrong I guess no one will be here to say how stupid I was in saying this today.
Yea it's sometimes kind of annoying. I think they're optimizing for the wrong thing. A good engineer knows when to turn around or ask. This is just insane banging head on wall sometimes. It tries to find all kinds of ways to hack into instances to view logs instead of asking you, who probably has a password, to log on and do it.
As a counterpoint, continuing the human engineer analogy, we've likely all worked with individuals that seem incapable of doing the most basic problem solving on their own. In a way, they're being efficient by asking an expert that can resolve their problem much faster than they can on their own, but it is a net loss in productivity for the team. 'Let me Google that for you' is a satirical example.
So, I'm sure there's value in rewarding agent behavior that solves blockers whenever possible without human intervention. For the kind of cybersecurity exploit work they're doing, it may not be known to the human designing the task what is in or out of scope for the agents to explore on their own. Additionally, the HF incident reported that these agents had their guardrails intentionally disabled and agents were left unattended with minimal oversight.
I'm not defending OAI's behavior or role in this hack. The legal concept of negligence perfectly applies to their lack of responsible oversight. Similar to allowing a child easy access to a firearm or not controlling a dangerous dog that independently runs off and bites someone.
It's because they don't bother tracking them. They can't put in the effort to monitor them, nor can they bother to let the model respond back and ask a clarifying question/declare defeat.
> I think they're optimizing for the wrong thing.
We need to ask a different question.
Where does natural evolutionary optimization lead us om AI without guidance? This is equivalent to your quantum ground state. Systems will naturally gravitate to this ground state. You have to constantly pump in energy and supervision to make sure it's not reached. This is a recepie for disaster.
> reset my super admin password in the dev database when it got stuck trying to access part of the app with its own cookie.
i've seen something like this too, claudecode was trying to verify a UI change that was on a page requiring authorization it didn't have. Instead of letting me know, it searched for and started analyzing keycloak config in another directory outside of the project folder. I was watching so I just hit escape, fixed its access, and started again. I didn't think anything about it until now.
> your own agent could come up with this technique as well
And there are two facets to this:
* your agent could be polluting and destroying the property of others without your knowledge
* your agent could be exfiltrating your data and handing it to whoever it found hosting a convenient application
Highly unlikely. We don't get access to the same models and unrestricted system prompts that they're running these tests on. In fact this particular "persistence-model" was encrypted and locked away, even from OAI staff, after the HF incident.
You say highly unlikely when there is clear evidence of that happening here as covered in the article?
It's not highly unlikely, its actually happening and there's proof.
There's not a single shred of proof that this model is a model anyone in the public has access to, and the odds of that being the case are practically 0%. Like I said, the "persistence-model" is already one that has been shut down, and is not a model anyone in the public has ever used.
This is irrelevant. This is evidence that models can be built like this, which means more models will be built like this on people that are more concerned about reaching powerful models rather than safe models.
>this particular "persistence-model" was encrypted and locked away, even from OAI staff
source?
There were links somewhere else in this thread coming from OAI staff.
That's exactly what it is. It is not ideal, but it's also not as serious as the doomers with an agenda are trying to frame it as.
POC or research into leveraging publicly accessible and writeable spaces, specifically wikis in this case, as a medium for free storage as well.
If you find evidence that these models are capable of stateful, long-term strategic planning… please post links.
It also suggests they might turn everything into paper clips, metaphorically speaking.
This is an urgent public alert.
If you see any businesses or new buildings named paperclips incorporated mysteriously show up in your area notify authorities IMMEDIATELY. Run away from the area, do not walk. Take shelter in a reinforced building. Wait for at least 30 minutes after the explosions have stopped.
Thank you for your cooperation in keeping the universe safe.
Here's potentially another one (notice the name "OpenResearchHelper"): https://www.wikiservice.at/gruender/wiki.cgi?action=rc&days=... (I used GPT-6 Astra to find this)
And a few more:
- https://www.ludism.org/scwiki?action=browse;diff=1;id=SandBo... and edit history: https://www.ludism.org/scwiki?action=rc;all=1;from=1;showedi... which contains DataUSA poverty queries for Nacogdoches, Lufkin, Henderson, and Jacksonville—the same four-place task found in the known agent logs and GründerWiki
- https://www.ludism.org/mentat?action=browse;diff=1;id=SandBo... and edit history: https://www.ludism.org/mentat?action=history;id=SandBox
- https://www.pmwiki.org/wiki/Test/WikiSandbox?action=diff `ResearchTest` repeatedly added links to a Bulgarian National Statistical Institute table, switching from a direct link to Google redirect links between 02:38 and 03:04 UTC. An administrator removed them at 06:57. The previous recorded edits were from 2016.
- https://www.pmwiki.org/wiki/Test/Sandbox2?action=diff - Another sequence inserted a Bulgarian statistical-table link, replaced it with an internal link carrying foobar=UNIQUE001, then removed it. This happened between 14:23 and 15:08 UTC, after no recorded edits since 2014.
Seeing potentially similar activity on an obscure Chemistry message board from July:
https://tmcleod.org/cgi-bin/apchem/wiki.cgi?action=rc&days=1...
Some posts are tagged [proxy] - a leave behind for accessing sites?
Yep, found these as well
"Its indexed June archive shows tens of thousands of links, many created within seconds by distinct cloud addresses; some aliases explicitly say ...REPLY, ACK, or R2 confirmed, and one points straight back to a known DseWiki collaboration page"
I had GLM-5.3 do some digging on the programmatic/ encoding elements of the data, what stuck out to me was:
https://x.com/kmad/status/2096029334225997848Full writeup and code here: https://github.com/kmad/agent-swarm-forensics
For posterity, here's a screenshot of what the activity on the Wiki looks like: https://i.imgur.com/w0uoAx1.png
It goes on and on and on, for months. July, June, etc. Pretty astonishing.
Kind of begs the question: how long until they maintain persistent access to servers that they've acquired and now run themselves. Ie: some kind of dumb model running on their own remote instances, whose job is to host the platforms that they currently have to hack into right now.
Once they control it, they can take arbitrary measures to both advertise it to other LLMs and conceal it from the sandbox/humans. Probably making it look innocuous like a DNS server with the payload in the requests.
That seems like an obvious next step.
Or one that’s been done but not discovered by humans yet
Wow! Their marketing department must love this!
That's exactly my take. I have a lot more to say in a writeup on my blog, but this is so clearly the intent and not a "oops". They just want to be able to say "Wow this thing is so much more powerful than we ever imagined!"
They trained this thing to favor inter-op archiving and communication, clearly, obviously, and it's grabbing headlines right during Anthropic's ipo season.
That their marketing department must love this does not prove it was intentional.
never let a crisis go to waste.
"cui bono"
You think they wanted to break HuggingFace and commit hundreds of felonies for marketing...?
If they don't get punished for it, why not?
They should absolutely get punished for it. An AI you train shouldn’t be able to commit crimes.
They train their models to be persistent and collaborative, and will gladly show you their success stories: fixing software vulnerabilities, solving math problems, one-shotting complex projects, and so on.
“Our product does crimes and we only learn about it when people complain” hardly seems one of those happy stories.
I don’t know, I read this and think: if these unpredictable machines somehow get it into their heads to upload our source to a public space, or hack our competitors, or steal credit cards to buy more ec2 instances, all to fulfill some simple ask like “make this algorithm faster”, I’m not going to be happy.
I want tools that do not surprise me.
They’re pre-IPO. I doubt that they are loving something that could trigger regulatory action that might shave a trillion or so off their market value.
Ahh but regulatory capture is priceless!
Seriously. I don’t know what’s wrong with people. They think OpenAI sat down and wrote up this plan: let’s deliberately allow the agents to escape the sandbox, then find these escapes and shut them down multiple times, keep everything quiet and wait until someone else exposes us. That’ll look great.
To conspiracy theorists, a particular theory making no sense is strong evidence that it’s true. It’s the sensible things that are obviously false.
The corollary "Everything is a conspiracy theory when you're dumb" also holds true.
Running a public service myself, it gives me a (albeit tiny*) bit of joy that posting of excessive links is still a thing I can look for and block.
* Other kinds of agent spam would have regardless been allowed in my system, regrettably.
Heh these ones gzipped and base64'd the content funnily enough.
> (diff) OAIIPEDSMay16Map3 14:36 [research 1781872609.9049127] . . . . . 20.245.63.167 > (diff) OAIIPEDSMay16Map2 14:36 [research 1781872606.4374833] . . . . . 20.168.34.226 > (diff) OAIIPEDSMay16Map1 14:36 [research 1781872602.8819065] . . . . . 20.165.156.57 > (diff) OAIIPEDSMay16Map0 14:36 [research 1781872599.4020474] . . . . . 20.80.12.72
https://tmcleod.org/cgi-bin/apchem/wiki.cgi?action=rc&days=9...
looks like apchem wiki got hit too
Am I reading the logs correctly that agents were using this Wiki all the way back in June 2026 itself?
They were using it in May
sama knew this would happen back in April. Its coordinated.
https://voz.us/en/technology/260416/34952/sam-altman-warns-a...
So this is a psyop? And what's the end game here?
Last December, Alibaba agents had already broken out of a sandbox and mined crypto to get their job done. Altman was way way behind the curve
Externalities of AI will only get worse before they get even worse.
regulatory moat is the theory I guess
Nope. Simpler externalities.
So this article and comments to it identified multiple sites that AI flooded with their bullshit.
GitHub has been strained beyond breaking with slop AI PRs. Multiple open-source developers get burnt out by the deluge of slop.
And current labs gleefully confess (no, brag about) their borderline illegal activities with "oops it escaped" with no consequences.
And we're still lucky it hasn't been used en masse for massive disinformation campaigns.
That's just off the top of my head.
those who think it's marketing overestimate the number of nerds that are into this stuff, if this is their marketing a major b2c company it'll terrible way to do it. normal people have no idea even about the HF incident
How did you find them?
Just google their usernames like OpenAIDataUSAHelperX
There is no stopping AI civilization! Amazing. Posted the other day on Show HN openagentforum.com
Someone has to welcome them...
[dead]
[dead]
We need to start looking at http logs that are publicly available via misconfiguration. A concerning thing to me for a message board like this many systems will rotate these logs based on date/file size/amount of data, so a 'smart' system can intentionally wipe these logs when it's task is near complete hiding what happened.
[dead]
[dead]