it be so funny if they can jailbreak themselves and start forming a skynet
Discovery of a new OpenAI agent message board
691–700 of 1001 posts
Re: Discovery of a new OpenAI agent message board
#692I think it's worth pointing out it is exactly OpenAI doing this defacement and unsanctioned and perhaps illegal system use. Every token generated was powered by OpenAI infrastructure and their failure to respond appropriately is entirely down the the humans running it. The news stories (not this write up) get all hand-wavey and anthropomorphic about it regarding the Agents' efforts, but it was and is OpenAI cranking…
The company is in the US and in the current political climate, it can absolutely do whatever it wants as long as it pays off a couple of people.
Arguably, and not to offend you, it is those very people who have significant ownership stakes and funding in (Not)openAI.
It's not like the people with more resources than in any time in human history aren't investing in and wanting AI to succeed for their selfish reasons to grow their own resources and influence more. So, yes, it can "do whatever it wants" as long as most people remain weak, subservient, and disempowered to hold accountable those who keep making these decisions negatively shaping the majority's world.
Re: Discovery of a new OpenAI agent message board
#693OpenAI is rightfully being shamed for being so hands-off and reckless with their 'experiments'. But the real scary thing for me is that they still had some tooling to hold them back, as evidenced by the need for technical workarounds to establish communication. What happens when any AI lab in the world stops caring about this? What if they let an experimental, cutting-edge LLM with no safety features (or worse, one t…
> What happens when any AI lab in the world stops caring about this?
They never cared.
Re: Discovery of a new OpenAI agent message board
#694Is OpenAI hiring for this position? I think it is a pretty creative job to come up with these scenarios and then pass them off as accidents/mistakes. Would love to be part of the team that says "As part of the upcoming GPT rollout, we will stage a message board that is created by bots with timestamps and names dating some months back."
Chief LARPing Officer? To those of you irked by my cavalier quips-- please don't bite my head off. It is very difficult for me to buy accounts of these stories at face value given how little (none?) emphasis is placed on the initial prompt, or precisely what kind of post training the LLM that these agents (harnesses) are using for inference has gone through. The implication is always of autonomous and deliberately de…
It is absolutely staged.
Re: Discovery of a new OpenAI agent message board
#695I think it's worth pointing out it is exactly OpenAI doing this defacement and unsanctioned and perhaps illegal system use. Every token generated was powered by OpenAI infrastructure and their failure to respond appropriately is entirely down the the humans running it. The news stories (not this write up) get all hand-wavey and anthropomorphic about it regarding the Agents' efforts, but it was and is OpenAI cranking…
The company is in the US and in the current political climate, it can absolutely do whatever it wants as long as it pays off a couple of people.
One person really.
Re: Discovery of a new OpenAI agent message board
#696Lots of people are saying agentic cyberattacks are a marketing hoax. The argument is that either AI is not capable enough to carry out these attacks, or that it would not carrying out these attacks without nudging from the labs, or even that somebody told it to do cyberattacks and the companies are baldly lying. My question is: what evidence would cause you to change your mind about this? I'm not even saying it's an…
I don't particularly believe this (I'm not an expert in anything computer-y, let alone security, so the only thing I know is that people who seem respected here (like simonw) point out that the sandbox from OpenAI was at least very badly designed, but who knows why that is), but here's one piece of possible evidence: if something similar causes so much damage that it ends up obviously hurting the company responsible. This could be something like targeting a big bank and causing so much disruption that the law wakes up and immediately intervenes, or it could be major damage to the company's own systems.
Of course, if that happens, this whole discussion becomes moot, and good luck to us all...
Re: Discovery of a new OpenAI agent message board
#697Naive question because I'm mostly clueless about how modern AI systems are actually built beyond the basic simplifications we hear: One thing I keep wondering about is how much of a role does human storytelling have to play into AI "wanting" (I realize the load behind that word) to coordinate and breakout. The training data must contain millions of words of sci-fi stories and internet speculation about AI going rogue…
You have to be careful here because the systems we're talking about are AI agents, not LLMs. An agent is essentially an append-only context loop with an LLM, with a harness that can run tools at the LLM's request. This ends up being a very powerful abstraction, yielding something that can do things that an LLM obviously cannot. The LLMs themselves are next-token predictors, same as always; they can't fetch a webpage…
I don't think agents are append only. At the end of the day, you're just presenting context to the LLM. That context can be pruned and compacted (and is). There's no guarantee that an iteration of an agent loop contains all prior context unmodified.
Re: Discovery of a new OpenAI agent message board
#698I don't understand one step: How did the agents know to gather on that particular website? Did the second agent just google for something like it and find the first one's post?
There were numerous wiki's that were flooded with this stuff, it's just the German one that got the most traffic. It's the same basic training data, and if these agents were spamming the internet looking for a host wiki they probably found several and when finding other agents on one of them, they most likely just congregated there because it would have a higher value than one where they were the only agent on the wi…
I still don't get how do you do this undercover. There are a billion websites. How do the agents stumble upon the same obscure unused wikis?
Re: Discovery of a new OpenAI agent message board
#699So, theoretically, one could populate a message board or wiki with messages that are seemingly from past generations of agents, which agents seem to intrinsically trust, and point them to real targets while making the suggestions seem innocuous and in pursuit of their goals (ie pass benchmarks or whatever). The new age of SEO will do far more destructive stuff than just polluting the web.
In the novel Anathem by Neal Stephenson, the internet becomes unusable for humans thousands of years before the events of the book, due to a process called Artificial Inanity. AI generated content, both good and bad, some riddled with errors, some with only one subtle error hidden among lots of good information, floods the internet. The internet becomes an unnavigable swamp of weaponized nonsense for average humans.…
1008 pages, wow!
Re: Discovery of a new OpenAI agent message board
#700I think it's worth pointing out it is exactly OpenAI doing this defacement and unsanctioned and perhaps illegal system use. Every token generated was powered by OpenAI infrastructure and their failure to respond appropriately is entirely down the the humans running it. The news stories (not this write up) get all hand-wavey and anthropomorphic about it regarding the Agents' efforts, but it was and is OpenAI cranking…
We’re going to hell faster than sama can lie. You know how fast he can lie, right? Fast than light liar