Unpopulate opinion: Fewer PRs done with proper prompting, review, and refinement usually win long term.*3 thoughtful PRs a day > 40 poorly thought ones no matter how many AI agents reviewed them.*
- codex 5.5 medium - best results less hand holding medium speed
- opus 4.8 max - mediocre with hand holding medium speed
- glm 5.2 max - mediocre with hand holding and super slow
- composer 2.5 - mediocre with hand holding and super fast
I use all, since i run mulitple coding in parallel. disclosure - I use rexide which we created for all these agents to run in parallel with good visibility and feedback.
Hey,We built RexIDE after juggling too many repos, terminals, and half finished reviews at the same time.The goal was simple: keep all projects, diffs, voice input for all cli, and AI help in one continuous flow — without switching tools or rebuilding context every time.RexIDE is built using RexIDE. I use it daily to manage multiple projects, review diffs, and ship changes from the same...