sukit

Been trying to get into jj lately, but I rely a lot on VS Code's git gutter to review changes as I code. Doesn't look like jj has an equivalent in VS Code. Anyone got tool recommendations?

Code can be logically separated, but my mind struggles to do the same. I guess this might require some training?

Using different models to supervise each other sounds reasonable. I’m curious what plans are you subscribed to for Claude and GPT?

I haven’t tried that, does it introduce some kind of “black magic” that makes the agent hard to observe?

Do you manage worktrees manually or leave it to Agent?

Fair question. I haven’t done a systematic benchmark yet, so I don’t have hard numbers to point to. Honestly I’ve mostly been iterating from actual use. The main test has been whether it helps me keep the good parts of brainstorming with the agent, recover context across longer multi PR or multi session work, and reduce friction overall. So right now the evidence is mostly qualitative and based on my own workflow, not a formal evaluation.

Thanks a lot! I’ll definitely give that a try.

I’ve seen so many people praise Claude Code so highly that my first instinct was to assume I must be using it wrong. I’ve tried quite a few different workflows and prompting styles — but still haven’t been able to get results anywhere near as good as what those people describe.

That's a great point. I think there is some pattern to when it works well or not, but I’m not sure if that’s universal or just tied to how I use it. Different prompting styles or workflows might lead to very different outcomes.

I might be misunderstanding how it works, but from what I’ve seen, CLAUDE.md doesn’t seem to be automatically pulled into context. For example, I’ve explicitly written in CLAUDE.md to avoid using typing.Dict and prefer dict instead — but Claude still occasionally uses typing.Dict.

Do I need to explicitly tell Claude to read CLAUDE.md at the start of every session for it to consistently follow those preferences?

That’s the problem — about 50% of the time, the result is so messy that cleaning it up takes more time than just writing it. So I wonder is there a better way to prompt or structure things so that I consistently get clean, usable code?

Appreciate it, I’ll check it out.

That makes sense — I’ve mostly been using Claude (Sonnet), so I’ll give the GPT-4 series a try and see how it compares. Thanks for the suggestion!

That’s a great idea. I haven’t tried connecting to a browser with something like Playwright before.

Yeah, you’re right — at some point I just have to learn CSS more deeply.

Thank you, John.