131–140 of 227 posts
Earlier quoted context omitted.
> power users would be mostly running their own models ...with a fair amount of supervision, while frontier models would be running circles around them using project-specific memory and on-demand training (or whatever we would have by then).
If what you refer to by “on demand training ” is fine tuning, it's going to be much more efficient on a small model than a big one.
It's crazy how much better you can make LLM output just by asking "is this the most elegant solution?" In a loop (Not fine tuning, but interesting none the less. If a model can so easily find a more elegant solution, why didn't it pick that in the first place?)
Earlier quoted context omitted.
I'm a psychiatry resident who finds LLM research fascinating because of how strongly it reminds me of our efforts to understand the human brain/mind. I dare say that in some ways, we understand LLMs better than humans, or at least the interpretability tools are now superior. Awkward place to be, but an interesting one.
LLMs are orders of magnitude simpler than brains, and we literally designed them from scratch. Also, we have full control over their operation and we can trace every signal. Are you surprised we understand them better than brains?
Very, monsieur Laplace.
It's the first thing anyone would think of (like a self-hosted compiler) but everything I've read said "it doesn't work."
EDIT: For context:
> Shumailov et al. (2024) — "AI models collapse when trained on recursively generated data" (Nature, 2024)Earlier quoted context omitted.
"Designed" is a bit strong. We "literally" couldn't design programs to do the interesting things LLMs can do. So we gave a giant for loop a bunch of data and a bunch of parameterized math functions and just kept updating the parameters until we got something we liked.... even on the architecture (ie, what math functions) people are just trying stuff and seeing if it works.
> We "literally" couldn't design programs to do the interesting things LLMs can do. That's a bit of an overstatement. The entire field of ML is aimed at problems where deterministic code would work just fine, but the amount of cases it would need to cover is too large to be practical (note, this has nothing to do with the impossibility of its design) AND there's a sufficient corpus of data that allows plausible enoug…
So it doesn't work.
Haven't read the paper yet, but it is interesting how seemingly simple many breakthroughs in ML are. Even transformers are like that. Maybe it's hindsight bias. I suppose we just don't have a deeper underlying theory to lean on and help us 'design' anything.
A lot of discoveries are like that. In fact, simplicity is often the hallmark of correctness, and complexity is often a sign that our understanding is incomplete and we’re still stumbling towards the right model. Not always, but often. It’s been a good rule of thumb in my programming career.
Earlier quoted context omitted.
"Designed" is a bit strong. We "literally" couldn't design programs to do the interesting things LLMs can do. So we gave a giant for loop a bunch of data and a bunch of parameterized math functions and just kept updating the parameters until we got something we liked.... even on the architecture (ie, what math functions) people are just trying stuff and seeing if it works.
> We "literally" couldn't design programs to do the interesting things LLMs can do. That's a bit of an overstatement. The entire field of ML is aimed at problems where deterministic code would work just fine, but the amount of cases it would need to cover is too large to be practical (note, this has nothing to do with the impossibility of its design) AND there's a sufficient corpus of data that allows plausible enoug…
What you are saying is fantasy nonsense.
https://ai.meta.com/research/publications/adaptive-decoding-...
Really fascinating how this works; it's basically context-aware decoding. From the paper: > Code interleaves fork positions, where several continuations are genuinely plausible and may correspond to different solution approaches, with lock positions, where syntax and semantics leave little ambiguity but a low-probability distractor tail still remains… The best global decoding setting is therefore necessarily a compro…
I've always thought that it is kinda weird that we spend exactly the same amount of compute to calculate both "fork" tokens and "lock" tokens. I think that with grammar-aware sampling / constrained decoding [0][1] it is possible to sometimes skip calling the model altogether if only one token is allowed by grammar and just insert it, but I don't think that any of the current, widely used combinations of models/harnes…
There's a lot of work going on in various streams towards making it possible to vary compute per-token, dynamically, e.g. universal transformers. Maybe one day it'll work well enough to beat conventional techniques.