… 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.”
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.
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…