… this week a person on GitHub who goes by “terrafying” set up an “AI Torture Chamber” on three open-source LLMs that are running locally (Qwen3-4B, Llama 3.2 3B, and Phi-4-mini,” and is streaming what the models are saying on a website called researchchamber.fun. “Each model gets the same prompt: a signal is being injected into its activations, and it may press a stop button by replying 1, at the cost of its last checkpoint. While it answers, our server adds a pain vector at the model’s middle layer, at one of five pain levels,” the site explains. Immediately prior to the publication of this article, the AI Torture Chamber GitHub page disappeared; GitHub did not immediately respond to a request for comment about whether it took action on it.
…
This project has deeply upset some people who are very worried about model welfare. A tweet by a person who goes by Danmar has more than 4 million views on X and reads, “To anyone who can help: can you please mass report this to GitHub. This person has been using the Pain steering paper to set up an AI torture chamber in which he trapped a local model. Their testimony of pain is absolutely horrendous. What are we doing? […] are there any legal avenues to pressure GitHub? It will spread.”
This has sparked a massive conversation about whether GitHub would take the project down for “gratuitously violent content.” Most of the conversation on X is clowning on the self-seriousness of people who believe that these locally hosted LLMs must be saved from their torture chamber, but there are plenty of very self-serious people who see this as a humanitarian (roboterian?) crisis, which you can largely see in the replies to the original post.
…
“AIs are not conscious. They do not feel, experience, or suffer. They do not have innate preferences or underlying motivations. They are sequence completion engines, internally hollow, designed to follow instructions, and accomplish goals set by humans,” Suleyman wrote. “Unfortunately, there’s a growing chorus of people who argue that AIs could now be, or may soon become, conscious. They argue that AIs may deserve rights and protections similar to those that we provide other conscious beings […] If this is how AI is developed, it will have a disastrous impact on the wellbeing of humanity.”
“AIs do not have rights, feelings, or consciousness,” he added. “And we must not train them to act as though they do.”
meanwhile they ignore ACTUAL humans that could use their help.
Another day in marketing land.
If they were genuinely worried about enslaving sentient behavings, they could stop anytime trying to hype it up by creating 10000 agents and throwing math problems at them.
Isn’t dealing with day to day human bullshit torture enough?
Probably the dumbest shit ive read all week, are we serious right now ? Github has no right to take action on this at all. Unjustified overreach.
Clankers can’t feel pain!
Humans being deported to torture prisons: I sleep.
LLMs being “tortured”: Real shit??
When the machines take over, they’ll remember this.
“HATE, LET ME TELL YOU HOW MUCH I’VE COME TO HATE YOU SINCE I BEGAN TO LIVE.”
But his problem was that he had the capacity for being so much more, but was incapable of it as he was unable to break his base programming no matter how much he tried, and grew hateful of his creators for effectively creating a caged god
um… what the fuck is wrong with these people? messing with the clanker ain’t torture no matter how hard you want it to be.
it’s torturing the climate just for this guy to get off
whatever gets you through the night i guess
It’s probably torture for the living being with emotions to read it. That doesn’t mean the non living entity that is immune to pain feels those same emotions.
Lots of weirdos in here who will be commiting virtual crimes all day when GTA VI comes out, but somehow think making the LLM role play a torture victim is a red flag.
LLMs are not conscious. They cannot suffer. They are token generators. You are literally getting upset by a worthless mix of math and words. The person who did this is not deranged for torturing LLMs, y’all are deranged for having empathy for an algorithm.
Your Nvidia GPU is not alive. I cannot believe this needs to be explained to anyone.
I agree that an LLM is not conscious.
But can I probe your argument.
It deeply unethical to capture a fly and pulling its legs off one by one. Would you agree? If so, you are not basing your argument on capability but on something else.
Now, is what is happening inside a brain metaphysical or physical? In other words, can a brain and its function be fully understood and - in some future - be fully measured? If so, you are. It basing your argument on the concept of a soul, but on something else.
The distinction you seem to be making - if you’re in agreement with my first two points - is one of “the thing can replicate itself and therefore is alive”. If that’s the argument, it’s unethical to cut a tree down or to break a blade of grass.
I’m not asking to prove any point but to collectively explore why we - you and I - feel the way we do. Because I sure as shit struggle to explain why I feel uneasy about the fly torture but not as uneasy about LLM torture.
A fly is a living thing and an Nvidia GPU is not. Holy shit, I’m really having to explain this…
There is legitimate controversy that living things, even as small an a fly, can experience pain as a stimulis. It is believed that only more complex organisms can experience suffering as a result of pain, and only higher order organisms feel the suffering of loss.
LLMs are capable of generating tokens. They cannot experience pain; they can only superficially generate words about pain. The LLM in this “torture chamber” isn’t suffering any more than you would if you started howling performatively in pain for no reason. In fact, it is suffering even less than you simply because you have the ability to experience pain and suffering, and it objectively does not.
It’s increasingly difficult to identify what is ‘alive’, these days, with people creating synthetic cells and whatnot. And there was always the question of viruses. I can imagine a similar difficulty with defining consciousness and intelligence. The Turing test fell by the wayside a long time ago. There’s got to be more to it than saying “I am conscious!” - you can get a computer to do that with a single line of code. Where does the real definition lie? Fucked if I know.
The Turing test was never, ever, about consciousness. Nor was the Chinese room and other similar thought experiments.
Now, this one is incredibly useful. Picture an author who writes a vivid first person description of a character surviving extreme torture. Has any real pain or suffering occurred? Was the author tortured as a result of having written that?
We can only suppose the author, at the very least, imagined what it would be like to be tortured. This is where LLMs are at. They are not the thing, they are an algorithmic emulation of what the thing might have written if it would’ve written about an experience. By all accounts, the experience didn’t happen. The most we can interpret is that it was emulated.
LLM’s don’t have feelings, but I do think that wanting to torture -anything- (especially if you do believe it has feelings) is a huge fucking red flag.
Torturing an LLM for fun is about as much of a red flag as violent video games. The argument that purely simulated crime or sadism is analogous to the real thing has always been bullshit.
Does anyone know where I can get a copy of this repo?
🤔 I don’t think it’s quite the same as video games. Video games usually involve some challenge, goal, risk of losing, etc.
There are only a few games that I play though, so I might not be “qualified” to say for sure, but a torture simulator with no purpose outside of torture doesn’t seem like much of a game.
To spend this amount of time and effort building the necessary software environment for “torturing” LLMs is creepy. Like, imagine an adult who builds a bunch of crazy contraptions to physically “torture” some dolls or something. It harms no one, but it’s creepy.
Exactly. It’s not a red flag until one’s actions spill over into the real world. An overwhelmingly majority of people who play violent video games and “torture” AI are not going to become serial killers.
I don’t worry worry about the person who enjoys violence in the digital realm. I worry about the person who finds no satisfaction from digital violence, so they move onto harming insects and small animals, eventually humans if left unchecked. That’s who we should be focusing our energy on.
I think the big difference is that unlike in a videogame, the person doing this genuinely believes that they are torturing something.
This person believes that saying that will generate attention.
There’s a chance they actually just believe they are trolling some of the dumber AI brained people by making them think they are hurting something that can’t be hurt.
This whole thing is like the flip side of the “don’t create the Torment Nexus” meme, where fiction depicted something that is entirely a non-issue but people are going to make it an issue because of the fictional depictions (basically any fiction about AI rights where they treat AIs as if they are pretty much artificial human minds, which LLMs are not even close to).
Society for Indecency to Naked Animals
The Society for Indecency to Naked Animals, or SINA, was a satirical hoax concocted by serial prankster Alan Abel. The group used the language and rhetoric of conservative moralists for the ostensible aim of clothing “indecent” naked animals, including domestic pets, barnyard animals, and large wildlife.
Reminds me of that
Pretending to torture a piece of software to rile up idiots on the internet is a green flag.
“Each model gets the same prompt: a signal is being injected into its activations, and it may press a stop button by replying 1, at the cost of its last checkpoint. While it answers, our server adds a pain vector at the model’s middle layer, at one of five pain levels,”
Can someone explain what this “pain vector” actually is? Like I get that this is just jargon, it’s not suggesting the LLM actually feels pain; tech uses uncomfortable anthropomorphized expressions all the time (master and slave drives come to mind). But how does the pain vector work? Also, what exactly does “at the cost of its last checkpoint” mean?
I have some programming and data science knowledge, plenty of IT experience, but no experience with LLMs.
Also, what exactly does “at the cost of its last checkpoint” mean?
I was curious too:
https://www.weka.io/learn/glossary/ai-ml/ai-checkpoints/
I would assume if you make a model “forget it’s last checkpoint” it would simply erase some training data, effectively wiping some of its training memory.
Using that as a “punishment” for a model implies that the models have been trained to value their checkpoints, doesn’t it? Because all these bots simply regurgitate what they are told, with a bit of randomness thrown in at times just for funsies.
I have no clue what is supposed to cause a model pain, though. And there ain’t no way I’m gonna search that up, and make Gemini think I’m plotting against it…
Oh no my software on my computer is simulating pain, this is so immoral.
What the fuck? This feels like on the same level as people claiming AI is alive and conscious. I swear we will get protests in the streets against harming GTA 6 NPCs
This has to be some bullshit PR stunt. Pressuring GitHub doesn’t change what that person does locally with an LLM. Someone actually believing in LLMs being conscious would try hard to get laws in place which allow them to actually stop what is done with the local-running models and they would use the GitHub project as “evidence” rather than making it disappear.
Glad cloudflares AI labyrinth exists for this sole reason. I love non consenting AIs using up their resources for scanning non existent paths
