Also, shoutout SkyPilot! It's been a huge help for going multi-cloud with our training and inference jobs (getting GPUs is still a nightmare...)!
Does the agent have access to arxiv (a brief skim of the README didn't have an answer)? If not, it could be that the current approach of relying on the model's weights only is resulting in the perceived local optimum of hyperparameter tuning.
Anecdotally, we built a little MCP for arxiv to help with our internal research, noticed a significant boost in the diversity of methods (architecture or otherwise) Claude and friends were able to reference.
Re: OpenCogPrime:EconomicAttentionAllocation https://news.ycombinator.com/item?id=45518074 and something about eWASM (edit) https://news.ycombinator.com/item?id=47171887 .. from https://news.ycombinator.com/item?id=46825026 re: eWASM and costed opcodes for agent efficiency
Here’s a use case that may illuminate the difference, from my own work at Nvidia. Im currently training some large sparse autoencoders, and there are issues with dead latents. Several solutions exit to help here, such as auxk, which I can certainly include and tune the relevant params as you describe. However, I have several other ideas that are much different, each of which requires editing core code (full evaluation changes, initialization strategies, architecture changes, etc.), including changes to parallelism strategies in the multi-rank environment I’m using. Moreover, based on my ideas and other existing literature, Claude can try a number of new ideas, each potentially involving more code changes.
This automated run-and-discover process is far beyond what’s possible with hyperparam search.
Most people are optimizing for terrible benchmarks and then don't really understand what the model did anyone and just assume it did something good. It's the blind leading the blind basically, and a lot of people with an AI-psychosis or delusion.
He is a researcher who understands neural networks and their architectures exceptionally well. That is all.
And that is precisely why he is more qualified on the subject than your average vibe coder!
E.g., you can see a post from a user named dhouston, who mentioned that he was thinking about starting an online file sync/backup service of some sort.
I might reframe the comment as: are you actually using LLMs for sustained, difficult work in a domain that has nothing to do with LLMs?
It feels like a lot of LLM-oriented work is fake. It is compounding "stuff," both inputs and outputs, and so the increased amount of stuff makes it feel like we're living in a higher plane of information abundance, but in reality we're increasing entropy.
Tech has always had an information bias, and LLMs are the perfect vehicle to create a lot of superfluous information.
In practice, the vast majority of the changes that auto research actually made would have been found much faster with BO if properly parameterized. You do not need an LLM to find a better batch size or learning rate.
To calculate an gradient step, in practice one doesn't accumulate the gradient for the full corpus, but updates the weights on mini-batches.
Suppose one runs conventional gradient descent on minibatches multiple times with different starting seeds, and then considers a set of pre-trained models M_i
From a random starting point we thus have an idea of the desired end-region in weightspace (lets say a gaussian cloud fit to the final M_i's).
Then it seems like one could score update strategies by how much a single iteration has approached the gaussian cloud, by scoring just the approach on a number of minibatches or just a few update iterations. Instead of searching update strategy space by waiting until pretraining has finished for each candidate update strategy. Only the candidate strategies that perform well enough on 1 or a few iterations would be considered worthy of further consideration, those that pass (a lower number of candidates) are then inspected for approach to the gaussian target after another round of iterations etc.
It seems like it should be possible to optimize the optimization iteration loop, by running it just once for many candidates and observing their convergence to the known desired end region.
Or is it the "anyone who means anything in the field, has access to high bandwidth anyway"?
Probably would cut the number of runs down by a significant number (as far as I can tell it's doing a grid search once it decides to mess with a knob or section of the architecture).
I don't necessarily disagree, but am wondering whether you have any particular reason/intuition driving you to claim this. I have seen AI agents be quite creative in other tasks; do you think there's a particular reason why we shouldn't see creativity in architecture research, given enough time and resources?
You can try this yourself in a simple fashion -- let's say you have piece of code that you want to speed up. Point your agent to a code profiler (your oracle -- typically your Python profiler) and tell it speed up the code. I've tried it. It works.