... 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.”
As with everything, the poison is in the dosage. All of your examples are categorically different from what's happening here.
You make a game with deep mechanics, and there is some fucked up shit that can be done in it, accidentally or on purpose ? Who cares. You make a game that is uniquely about torture ? Yeah you're a weirdo and i'm keeping tabs on you if i can. You make something that isn't even gamified and is just a virtual torture dungeon ? You're 100% a psycho, normal people don't do that.
Same with movies. Saw is a tame product of Hollywood professionals who decided to push the cursor a little further than is usual. Love it or hate it it's just a movie. Now if we're talking real devious shit like human centipede or Poughkeepsie tapes etc... Those are products that barely have a story, and are mostly sadistic exhibitionism. Some guy (who sometimes isn't even a film maker) has this repulsive idea he wants to force on people, gets their family and friends to pitch in a bit of money, then writes, directs, edits, and markets the thing solo over years of his life. Not something normal people do.
My wife is, among other things, a horror writer. So naturally i agree there's nothing wrong with exploring morbid ideas and pushing the envelope. But some people do that with no fun, no game, no art to it, no statement, just the obsession of unlimited sadistic control. And it's weird, not ha-ha anti-conformist weird, just "cover your drink" weird.