… 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.”
I wonder what percentage of the LLM rights activists eat meat.
I swear no one knows about this shit…
Put simply: LLMs are not conscious and the technology they are built upon — scraping and being trained on human text and other content — does not offer any plausible path to consciousness.
The problem isn’t the training, humans develop their own actual consciousness the same way.
The problem is current “AI” operates under the assumption consciousness is an electrical process.
Just a few years ago Penrose was proven correct that there is a quantum co.ponet when we discovered microtubules in the brain can arrange into a tube that sustaina quantum superposition.
Human could develop an inorganic consciousness, but we need to be able to sustain quantum superposition.
Right now the record is 23 minutes, after which it’s gone. But even after it’s stable, that would still only be the first in a very long string of challenges to what grifters claim we have now. It’s like building a Bugatti out of legos, even if it can really rolls downhill, it’s not a real Bugatti because it’s made out of legos.
1s and 0s will never be conscious.
I’m not going to argue against your conclusion, I strongly believe we do not have anything resembling human consciousness in software yet.
But Penrose was definitely not proven right (unless you’re talking about black holes), nor was the Orch OR theory about microtubules proven, nor was consciousness proven to be a quantum phenomenon. Here’s an easy, accessible article that goes over the state of the research: https://www.breezyscroll.com/science/new-quantum-evidence-is-reopening-the-debate-over-penroses-theory-of-consciousness/
Since the 1980s everyone called him crazy because obviously quantum entanglement can’t exist in a brain…
We recently found out that’s not difficult, and even superposition is possible.
We know that anesthesia breaks up those microtubules and breaks superposition…
And we know that anesthesia stops consciousness…
But we don’t “know” the actual method of action of anesthesia because it’s not proven.
Like, I understand what kind of rigors you’re trying to apply here, but if everyone did what you’re doing wed have to pretend gravity isn’t real too.
If you think only proven things are “real” you don’t even fucking understand what the words you’re using mean in a scientific context.
Edit:
What even is your alternative?
-
Quantum superposition is in the brain
-
Neurons alone don’t explain consciousness
-
Interrupting superposition interrupts consciousness
C: we know there’s no quantum component of consciousness.
None of that makes sense, to the point I’m confident you don’t know how basic logic works, or what most of these words even mean…
-
I haven’t read anything from the guy who did this, but my logical assumption is that he was trying to overload or DoS-attack the server, or maybe make it use up a zillion tokens to incur costs for its owner - the idea that he was trying to “torture” an LLM is ridiculous unless the guy’s a loon.
The LLMs were locally hosted, that’s like shitting in your toilet so much that you block your own pipes - it very literally doesn’t affect anyone else in any way.
ELI5 how a LLM is supposedly being tortured and not generating roleplay text according to a prompt?
They do differentiate between the LLM roleplaying someone in pain and the pain happening to itself.
But it’s still all just vectors (multi dimensional representation of a concept). It’s just pulling weights, or well let’s say putting more weight towards a certain concept when building it’s reply.
Would you mind ELI5-borating a bit?
Imagine a book with very large pages filled with words and half words. When you ask it a question, it flips through these pages one by one and highlights words. The pages are interconnected in a way, so the word highlighted on one page help guide which will be highlighted on the next. It does this for every word, symbol or half word of it’s reply.
By threatening it repeatedly while mildly changing the subject manner, they isolated the word groupings that represent pain and fear.
They then take those words, highlight them and put them at the top of the first page which guides the rest of the highlighting and makes it act silly.
This is an obsolete view of what’s going on and has been for a few years now (since 2023).
The evidence for world modeling in transformers and not just surface level statistics is overwhelming across multiple studies, replications to those studies, and follow-ups to them. If you are curious, start with searching for Othello-GPT.
The more correct current answer is more like “imagine a machine that takes a book and turns it into a world simulated in various levels of detail depending on how relevant those parts of the world were to the original book; when you ask it a question, it simulates the world of the book to determine what in the simulated world answers your question, and also simulates a figure in the world that can answer the question, and then returns the answer the simulated figure said.”
There are multiple genocides happening and some folk are getting worked up over AI potentially suffering?
Endless levels of fuck off.
Is it okay to be upset about both issues, or am I only allowed to be upset at one?
Edit: That’s a lot of downvotes for just asking a question. Never change Lemmy…
Are you upset when you step on a rock? It might be screaming. What about the chair you are sitting in? Or goodness, your poor toilet. She thinks you do terrible things to her every single day.
Look, you can be upset about whatever you want. However believing objects have feelings is animism and no one is required to take your proto-religious beliefs seriously.
What you aren’t allowed to do is compare a text prompt saying “ouch” to real living, feeling, breathing humans being ethnically cleansed. It’s cruel, naive, insulting and ridiculous. Be upset for the AI, I can’t stop ya but don’t you dare put in the same sentence as genocide. You should have the basic decency and respect for the people suffering to keep those comparisons to yourself.
Are you upset when you step on a rock? It might be screaming. What about the chair you are sitting in? Or goodness, your poor toilet. She thinks you do terrible things to her every single day.
Let me say this, I walk down the sidewalk without neurotically watching every step I take, and I’m certain that sometimes I step on insects; I don’t care. I don’t believe insects have feelings or meaningful lives, I don’t care, and I don’t think this position is particularly evil either.
On the other hand, when I watch my kid deliberately torture a bug, pull it’s wings off, or poke it with a stick over and over and over. That does concern me, not because of the bug really, but because what must my kid be thinking right now?
To bring this back to this LLM story, people who want to torture are scary, they worry me. A culture that encourages torture (in any context) is worrying, that’s a genuinely problematic societal norm. Logically, I know LLMs can’t feel and can’t think, yet emotionally, this bothers me for a few different reasons.
I don’t think I’m being crazy, naive, or out of line here. I think this is a rational position.
