Someone ‘Torturing’ LLMs in a Robot Prison Has Triggered the Dumbest Debate in AI Yet
www.404media.co
The "AI Torture Chamber" has opened an upsetting and absurd window into the effective altruist obsession with "model welfare."

… 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.”

  • Hueristic_AutisticEnglish
    4·
    3 days ago

    the router don’t have feelings. the router is literally the biggest waste of money and I wish I had put in the effort to find a router that doesn’t FUCKIN SUCK!!! I do everything they say to make this fucker better too. Put it up on a shelf, put it at least two rooms away from the microwave, unplug it every two weeks for 20 mins to cool it off, don’t use bluetooth directly within 12 ft of it. It’s one of the models made within the past decade, it’s supposed to be good it just fuckin sucks. You know what gimmie a second !!!

    I just busted out my goddamn tape measure!!! I am sitting two rooms away in my kitchen, 24 fucking feet not even 50 feet away from this piece of fuckin shit and I’m getting 550 mbps out of the 750mbps my wifi is supposed to pick up.

    I go one more room away, to the bathroom, which is nearing 39 feet away from the piece of fuckin’ shit, the internet disconnects while I shit.

    Yeah, I liberally, “verbally abuse,” my inanimate object that has no feelings.