Context Is Software, Weights Are Hardware
Comments
qsera
maxaravind
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.
qsera
That was exactly what I was thinking. So it is a bit unclear why such a possibility should be even considered.
To be fair, I didn't really understand what idea this article is trying to get across..
maxaravind
There has been a lot of talk about how continual learning might be "just and engineering challenge" and that we could have agents that continuously learn from experience by just having longer and longer context windows.
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.
qsera
>just extending the context length and adding more instructions in the context will not get you continual learning...
I agree. But I am wondering if context would help in answering superficial questions and only fail when answering questions that require deeper understanding.
maxaravind
Author 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.
kleyd
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"
maxaravind
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.
adityaathalye
> 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
maxaravind
lol nice analogy. LLMs are frozen diamonds forged in compute. We need then to be malleable in production and change with experience.
adityaathalye
Another way I see it is... Mind is process. LLM is (very lossy) snapshotted state of process/mind. LLM in-process is mind-emulator with potential to explore the state-space of the mind-snapshot. Consequently, and by its very construction, LLM cannot be mind.
4b11b4
I've never heard anyone say we can solve long-term memory by extending context to infinity. Curious about sources for this?
>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?