... 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.”
the line between normal and deranged is essentially what makes you specifically uncomfortable
Nah cause if that was the case, even Saw would be in the "deranged" category. God i hate those things, but it's okay i just don't watch them.
No, the line is like the one between a movie with a graphic sex scene, and a gonzo porn. 99.9% of content sits neatly into one of the two categories, and you'd have to really any media literacy to not be able to tell them apart.
Back to the subject : what this guy is doing on Github goes way beyond prompting ChatGPT with "i break your arm" and then GPT replies "oh noes that sucks". He's poured quite some time studying the mathematical representation of "pain" or "anguish" in the model weights and then steering responses towards that. He's experimenting on keeping an "entity" locked in total unescapable pain. I don't think the entities actually exist but what about him ? What are his goals and motivations here ? A crypto-bro, AI-booster, probably fascist-adjacent, toying with (what he believes to be) helpless entities under his control... If those things put together don't give you bad juju then i don't know what will.