Some people say we're near the end of pre-training scaling, and RLHF etc is going to be more important in the future. I'm interested in trying out systems like https://github.com/OpenPipe/ART to be able to train agents to work on a particular codebase and learn from my development logs and previous interactions with agents.

If they're unmotivated enough to not get there after four review rounds for a junior-appropriate feature, they're not going to get better. It's a little impolite to say, but if you spend any significant amount of time coaching juniors you'll encounter exactly what I'm talking about.

I have spent plenty, rest assured.

LLMs can learn if you provide it rules in your repo, and update those rules as you identify the common mistakes the LLM makes

Thanks for the insightful reply that showed me where I went astray.

Can you elaborate or you call it a day after insulting?

Aggreed