One of the most heated discussions occurring on X at the moment is about the ethics of a GitHub project in which a person is running Saw-like “torture” and “pain” experiments on a series of locally hosted large language models, causing a series of effective altruists and people who believe LLMs are sentient to beg GitHub to delete the project on the grounds that the AI is suffering and that this glorified text adventure game is somehow cruel. The saga is an outgrowth of several recent viral papers and blog posts that have sparked a wildly tiresome conversation about AI consciousness and the idea of “model welfare,” which is essentially worrying about the “mental health” of AI bots and agents.
To be honest it is still very disturbing that someone made that. Who tf thinks up something like that?
People (particularly western society) have a pretty awful history when it comes to jumping on excuses to dehumanize, and I feel like regardless of whether this target is sentient or not, we should probably not play into that impulse any further–for the sake of ourselves and also all of the humans we continue to dehumanize.
I agree. Does it have to be called a “torture chamber” for instance? I agree that the chatbots aren’t sentient but unless the real experiment here is “how many people see them as sentient,” I do not know why we need aliken it to eternal torment.
In a vacuum maybe, but as a way to troll AI nuts it’s pretty funny.
But more practically speaking, this might be a method one would use to produce “misaligned” models. Which shouldn’t be encouraged.
If you think this does anything to the models, you have not understood the difference between training and inference…
Are you suggesting these tortured LLMs will get… traumatised…? And turn into a fucking Batman villain?
Or does the paper this is based on – which I admit I haven’t read – actually have some substance to that effect?
That implies any of the existing models are properly aligned