Context Is Software, Weights Are Hardware(aravindjayendran.com) |
Context Is Software, Weights Are Hardware(aravindjayendran.com) |
Does this imply that a completely untrained model (random weights) should show intelligent behavior only by providing enough context?
It's kind of like asking if I make a random circuit with logic gates, does that become a universal computer that can run programs.
To be fair, I didn't really understand what idea this article is trying to get across..
I spent the last weekend thinking about continual learning. A lot of people think that we can solve long term memory and learning in LLMs by simply extending the context length to infinity. I analyse a different perspective that challenges this assumption.
Let me know how you think about this.
It is also my very uninformed intuition: https://news.ycombinator.com/item?id=44910353
Also interesting to think about: could a single system be generally intelligent, or is a certain bias actually a power. Can we have billions of models, each with their own "experience"
The brain theory also kind of says the same thing, but it's hard to say what stays fixed vs changes with experience in the brain ig.
Well, I think of every Large Language Model as if it were a spectacularly faceted diamond.
More on these lines in a recent-ish "thinking in public" attempt by yours truly, lay programmer, to interpret what an LLM-machine might be.
Riff: LLMs are Software Diamonds
www.aravindjayendran.com sent an invalid response.
ERR_SSL_PROTOCOL_ERROR
Here is a clip of Dario hinting at something similar: https://www.youtube.com/watch?v=Z0x99Uu4rJc
What I am trying to argue for in the article is how such a view might be misplaced - just extending the context length and adding more instructions in the context will not get you continual learning - the representational capacity of weights will be the limiting factor.
Just a fun way to think about it. Would love to hear your thoughts.
I agree. But I am wondering if context would help in answering superficial questions and only fail when answering questions that require deeper understanding.
Consider this, if something fundamental has changed in the world after the model was released(ie after the knowledge cut off date), then it would be very difficult for the model to reason about it. One concrete example is the the following: If you ask Opus or any decent coding model to do effort estimation on a coding task, then it would come up with multi week timelines - the models themselves doesn't know that because "they exist", these timelines have now been slashed to a few hours - you can try saying this in the prompt, however, they don't seem to internalise this.
Imagine an LLM that can also OCR. Would it be possible to make it OCR a totally new letter by only showing a single picture of it and including the fact in the context?
I think it would not be possible. That would be a good demonstration of the point I (and possibly you as well) is trying to get across.