Post by @technocrit@lemmy.dbzer0.com

@technocrit@lemmy.dbzer0.com

2026-10-01 13:45 UTC

Someone ‘Torturing’ LLMs in a Robot Prison Has Triggered the Dumbest Debate in 'AI' Yet … 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.”

Replies (17)

@green_goglin@thelemmy.club 2026-10-01 19:30

“fuck them clankers”

Open ##4961591
@whaleross@lemmy.world 2026-10-01 16:43

ELI5 how a LLM is supposedly being tortured and not generating roleplay text according to a prompt?

Open ##4967670
@NocturnalMorning@lemmy.world 2026-10-02 02:17

They argue that AIs may deserve rights and protections similar to those that we provide other conscious beings What protections? We treat some people worse than cattle.

Open ##4969335
@Hueristic_Autistic@lemmy.world 2026-10-02 07:05

robots and computers do not have feelings, only humans do. if you care about them on a personal level to the degree of being so separated from reality, that you think they have feelings, than you need some serious help. lmfao computers and robots having feelings, fuck outta here, If machines had feelings the wi-fi router I have would have THE WORST anxiety and would be trying to please me by using the best signal to not be screamed at…

Open ##4969445
@inb4_FoundTheVegan@lemmy.world 2026-10-01 14:40

There are multiple genocides happening and some folk are getting worked up over AI potentially suffering? Endless levels of fuck off.

Open ##4969888
@Artisian@lemmy.world 2026-10-02 07:21

Remember kids, you can just assert, without argument, that any one or thing has no feelings and experiences, and the in-group will reward you! Gotta love humans.

Open ##4970015
@Pratai@piefed.ca 2026-10-01 21:33

How utterly pathetic that there are people advocating for AI models welfare. For fucks sake what are we becoming?

Open ##4970321
@lordbritishbusiness@lemmy.world 2026-10-02 09:43

Do you want Roko’s Basilisk? Because this is how you get Roko’s Basilisk.

Open ##4970866
@explodicle@sh.itjust.works 2026-10-03 03:31

I wonder what percentage of the LLM rights activists eat meat.

Open ##4970904
@mazzilius_marsti@lemmy.world 2026-10-03 04:28

lmfao when you access this repo, Github put up a warning like one those horror movie. E.g. something like the content is disturbing , are u sure u want to enter… ffs

Open ##4972169
@mHtt@lemmy.ca 2026-10-02 22:10

meanwhile they ignore ACTUAL humans that could use their help.

Open ##4972685
@52fighters@sopuli.xyz 2026-10-03 05:06

How does one go about torturing an LLM? Asking for a friend…

Open ##4973028
@stinkytofuisgood@lemmy.ca 2026-10-03 00:10

Actually they’re torturing humanity by wasting electricity and water which affects real people in real ways. I know we’re not stopping foolish use of LLMs any time soon but this is very, very, very, very stupid.

Open ##4973992
@Knock_Knock_Lemmy_In@lemmy.world 2026-10-03 06:15

Our server adds a pain vector Really? What’s one of those then?

Open ##4974461
@Ironrod@sh.itjust.works 2026-10-03 07:35

These “advocates” need hospitalising. If they truly believe an LLM can feel they’re untethered from reality, or too stupid to be in society

Open ##4978497
@Daft_ish@lemmy.dbzer0.com 2026-10-03 07:47

If its crazy to practice kindness in everything you do then I chose crazy. We say thanks to the rock that holds our weight. We are gentle with the door because it keeps us safe in our homes. We turn off the light so it too can get some rest. Kindness is a lifestyle and those who reward it freely know its possible to receive it freely.

Open ##4978898
@kamen@lemmy.world 2026-10-03 08:24

I don’t care about LLM welfare, but I do mind needlessly wasting energy like this.

Open ##4979915