we need a real agent that represent our own interest and deal with a more powerful general agents. And we can delegate answering this question to those more personal agents.
I think this is mostly being overengineered. At this stage, a curated MEMORY.md is enough: short, readable at session start, and easy to correct when it becomes stale.
The session history is another database like any other database, can be used or invoked by agent like one.
> Both scores come from a fixed fallback rule: Opus 4.8 and Sol xhigh run first; games scoring below 80 are rerun with Fable 5 and Sol max, respectively, and the higher per-game score is retained.
hmm, this is like pass@n until you get the high watermark? How would this mean anything?
very good articulation on the problem. My bet is that it is probably fine in the sense that the mastery itself is not going to be relevant.
I want to view AI coding as invention of new coding tools, at least in the way you described. I (hope) it will be more like punch-card->assembly-> BASIC/C -> scripting language -> some sort of well-structured natural language.
Give Copilot a try, it completely shift coding experience in Rust.
Especially this:
> I always have to search libraries and how to do things.
Once you pass the initial curve with crutch like Copilot, then you can be almost as productive (if not more, considering refactoring and testing) with your native first coding language