> what currently is stopping Anthropic, OpenAI et al. from internally building (and maybe buying) datasets of good and bad architecture, and RL'ing that?
I think to do this well, you have to have all the comms, code for various projects over time and do large scale analysis with tooling to get the various outcomes. A lot of "good and bad architecture" is really post-hoc rationalization of decisions that worked, and it's likely super noisy.
I'd love to see this done, regardless of how difficult it is.
I think to do this well, you have to have all the comms, code for various projects over time and do large scale analysis with tooling to get the various outcomes. A lot of "good and bad architecture" is really post-hoc rationalization of decisions that worked, and it's likely super noisy.
I'd love to see this done, regardless of how difficult it is.