Context Is Software, Weights Are Hardware
aravindjayendran.com
Context Is Software, Weights Are Hardware
1–10 of 18 posts
Re: Context Is Software, Weights Are Hardware
#2Author here.
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.
Re: Context Is Software, Weights Are Hardware
#3Author here. 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.
> Let me know how you think about this.
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
Re: Context Is Software, Weights Are Hardware
#4Author here. 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.
Your conclusion touches on this, but I think the brain analogy is stronger than the hardware/software dichotomy.
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"
Re: Context Is Software, Weights Are Hardware
#5Author here. 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.
Your conclusion touches on this, but I think the brain analogy is stronger than the hardware/software dichotomy. 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"
I think both the views have their merits. In my mind the hardware vs software analogy for weights vs context holds better because in most modern computing systems, the hardware is fixed and the software changes. What the system can do efficiently, in practice, is a function of both the limitations/capabilities of the hardware and the software their respective capability ceilings.
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.
Re: Context Is Software, Weights Are Hardware
#6Author here. 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.
> Let me know how you think about this. 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 https://www.evalapply.org/posts/llms-are-diamonds/
lol nice analogy. LLMs are frozen diamonds forged in compute. We need then to be malleable in production and change with experience.
Re: Context Is Software, Weights Are Hardware
#7>for the sake of argument, that context can express everything weights can...
Does this imply that a completely untrained model (random weights) should show intelligent behavior only by providing enough context?
Re: Context Is Software, Weights Are Hardware
#8Author here. 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.
I've never heard anyone say we can solve long-term memory by extending context to infinity. Curious about sources for this?
Re: Context Is Software, Weights Are Hardware
#9>for the sake of argument, that context can express everything weights can... Does this imply that a completely untrained model (random weights) should show intelligent behavior only by providing enough context?
Nope. Even if context can theoretically encode arbitrary computation under fixed weights, this requires the weights to implement a usable interpreter. Random weights almost surely do not. Training is what constructs that interpreter. Without it context has no meaningful computational semantics.
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.
Re: Context Is Software, Weights Are Hardware
#10Author here. 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.
I've never heard anyone say we can solve long-term memory by extending context to infinity. Curious about sources for this?
here you go: https://www.youtube.com/watch?v=Z0x99Uu4rJc