Comment by rudhdb773b
6 hours ago
> what actually is happening inside an LLM has nothing to do with conscience or agency
What makes you think natural brains are doing something so different from LLMs?
6 hours ago
> what actually is happening inside an LLM has nothing to do with conscience or agency
What makes you think natural brains are doing something so different from LLMs?
Structurally a transformer model is so unrelated to the shape of the brain there's no reason to think they'd have many similarities. It's also pretty well established that the brain doesn't do anything resembling wholesale SGD (which to spell it is evidence that it doesn't learn in the same way).
>Structurally a transformer model is so unrelated to the shape of the brain there's no reason to think they'd have many similarities.
Substrate dissimilarities will mask computational similarities. Attention surfaces affinities between nearby tokens; dendrites strengthen and weaken connections to surrounding neurons according to correlations in firing rates. Not all that dissimilar.
Sure the implementation details are different.
I suppose I should have asked by what definition of "consciousness and agency" are today's LLMs (with proper tooling) not meeting?
And if today's models aren't meeting your standard, what makes you think that future LLMs won't get there?
Given the large visible differences in behavior and construction, akin to the difference between a horse and a pickup truck, I would ask the reverse question: In what ways do LLMs meet the definition of having consciousness and agency?
Veering into the realm of conjecture and opinion, I tend to think a 1:1 computer simulation of human cognition is possible, and transformers being computationally universal are thus theoretically capable of running that workload. That being said, that's a bit like looking at a bird in flight and imagining going to the moon: only tangentially related to engineering reality.
2 replies →
If platonic representation hypothesis holds across substrates, then it might matter very little, in the end. It holds across architectures in ML, empirically.
The crowd of "backpropagation and Hebbian learning + predictive coding are two facets of the very same gradient descent" also has a surprisingly good track record so far.
For starters, natural brains have the innate ability to differentiate between things that it knows and things that it have no possibility of knowing...
https://personal.utdallas.edu/~otoole/CGS2301_S09/7_split_br...
See page 53. While it is absolutely more prevelant in LLMs, human brains can also want a story for why their brains do things they are't plugged into.
Lol. Are you sure about that or you just made it up?
Modern LLMs are fairly good at that as well.
But that is bolted on and is not a core behavior.
1 reply →
Any amount of reading into how we understand brains and LLMs to work.