posted in Technology
Why your local LLM feels dumber than it is
forum.level1techs.com/t/why-your-local-llm-feels-dumber-than-it-is/253917
If you ascribe any level of sentience or intelligence to a computer, you definitely feel much less dumb than you actually are.
And who are you to assert that? How well defined is sentience already?
Replying to @SlimePirate@lemmy.dbzer0.com
I mean, I’m all for local LLMs, but they are as sentient as a really good weather prediction model.
aka not at all.
Its just a fact of how they operate, mechanically. They are missing too many characteristics for it to even be an entertainable question.
They might operate differently but they still appear the same as us, 99.9% of the time. Imo if it looks like a duck and acts like a duck…
Do you not interact with any other actual humans?
I do, and I can say that the conversations with AI (especially using tools like character.ai) are 99% the same
Well, that may very well be the most depressing comment I’ve ever read.
You either need to work on your listening skills or find some new less-vacant people to interact with, because what you’re saying is insane
Sounds like you haven’t tried modern AI yet. I could train an AI on your comment history and copy you, and nobody would be able to tell the difference
You’re underestimating most people
You overestimate most people. Here’s a study from 2025
Among AI models, Blenderbot stood out: in AI-AI conversations, it was judged human 67% of the times - more often than actual human-human conversations. In human-AI conversations, human participants were labeled as humans 68% of the time, and AIs were classified as AI 56% of the time.
This is an interesting study. I wonder why there’s such a disparity between the number of AI ‘participants’ (10) and human participants (1,916). I wonder how adding additional AI models would impact the data.
Anyway, this is just benchmarking the AI on 6 language specific tasks. They were programmed and set up specifically to perform whatever specific one task they had to do at the time, that is what computers do. The fact that computers are 1% better at recognizing other computers than humans are is irrelevant.
AI cannot pass the Turing Test, this article is about “6 Turing like tasks” and it can’t even pass those yet, lmao. You know they’re already seeing diminishing returns in further training right?
Even in this article is says that even if AI could pass a real Turing Test it wouldn’t be a sign of intelligence or cognition.
Something I should point out just in case is that 50% success rate is the same as random chance. So when the study says:
AIs were classified as AI 56% of the time.
That really means that humans could not tell the difference between AI and human, since their success rate was almost the same as random chance.
6 language specific tasks. They were programmed and set up specifically to perform whatever specific one task they had to do at the time, that is what computers do.
Sure, and that task was “imitate humans”, and these computers seem remarkably good at it. That’s what I’m saying. I don’t care that these AI work differently than humans. They can imitate humans so well that humans can’t tell the difference.