Hacker News Reader

Comment by vkgcr | Hacker News Reader

But theoretically, what would prevent the labs from RL'ing the models on "weight-space programming" tasks so that they get better at them? Perhaps we're just at the beginning, like how coding agents sucked 2 years ago.

It still seems like a promising approach for RSI, distillation, fine-tuning, and a whole host of other tasks.

View on HN

The context.

It's impossible to train on raw document > 1MB (I don't know the exact limit, but there is one). You can't vectorize weights (or can you?!) and the output context is limited. So you can't train a big model on it's previous weight or others models weights.

The output context can be "extended" using agents but I doubt anything coherent may be outputted using that technique.

Of course this is the problem. It's amazing that for all the commentary around AI models the number of people who really understand even the basics approaches zero.

They might even discover some way to program the weights proportional to an error signal

Now that would be crazy

I know you're being sarcastic, but I meant prompting an LLM with "generate me a X billion parameter model for doing Y task" and it would just output the weights.

Now THAT would be crazy

Yeah, this was my thought (as a layman) as well.

It seems some level of interpretability, even if it requires tooling, could result in the ability to spin out synthetic training data sets from other models in an automated fashion.

Reply on news.ycombinator.com