Hacker News Reader

Comment by alkonaut | Hacker News Reader

I installed the copilot extension in my IDE, and switched on Agent mode.

I don't really get how the workflow is supposed to work, but I think it's mostly due to how the tool is made. It has like some sort of "change stack" similar to git commits/staging but which keeps conflicting with anything I manually edit.

Perhaps it's just this particular implementation (Copilot integration in VS) which is bad, and others are better? I have extreme trouble trying to feed it context, handling suggested AI changes without completely corrupting the code for even small changes.

View on HN

Copilot in vs code is definitely trash. That aside the workflow is simple. If you are familiar with the code base then make sure to refer the files where a newb has to look if you were assigning the task to them. Tell it to ask questions. Usually framing the spec into a conversation will make things clearer in your own mind.

Hm, yeah maybe. I've tried Cursor once, but the entire experience was so horrible, and it was really hard to know what's going on.

The workflow I have right now, is something like what I put before, and I do it with Codex and Claude Code, both work the same. Maybe try out one of those, if you're comfortable with the terminal? It basically opens up a terminal UI, can read current files, you enter a prompt, wait, then can review the results with git or whatever VCS you use.

But I'm also never "vibe-coding", I'm reviewing every single line, and mercilessly ask the agent to refactor whenever the code isn't up to my standards. Also restart the agent after each prompt finished, as they get really dumb as soon as context is used more than 20% of their "max".

If you're dumping the context every prompt, that might be why you're not happy with the results of Cursor. I can run a dozen or two prompts before the context gets polluted enough that it's worth compacting. If you clear it's context every time, it's not going to get a holistic enough view of the problem to deliver a good feature.

That's been my experience. You have to work them up to the big ask.

Instead of "asking to refactor", you might get better results by defining your standards in a ... standard way.

Give the agent tools to determine whether code is up to your standards, an executable or script it can run that checks for code style and quality. This way it won't stop the agent loop until the checks pass - saving you time.

Make sure you’re clicking “Keep” to “approve” the changes. It’s annoying but I don’t think there is a way around having to do that. Then if you manually edit something, you can mention it in your next chat message, e.g., “I made a few changes to <file>. <Next instruction>”

Correct. Of the various ways to work, I find the in-IDE chat to be the worst. I rarely use it for anything other than “help me understand this line”.

Try one of the CLIs. That’s the good stuff right now. Claude Code (or similar) in your shell, don’t worry about agentic patterns, skills, MCP, orchestrators, etc etc. Just the CLI is plenty.

Copilot is a dumpster fire and I can understand why you're down on agents from that experience.

Splurge on the $20 for Cursor, and install their IDE. Start with a simple project, more because it helps you see how it works than because Cursor can't handle more. Give it specific instruction and not too big a problem at one time so you can tailor the prompt. If it's niche, consider changing the model to Opus4.5 long enough for it to get a handle on the codebase. Use the Plan mode to start, adjust the plan, then let it god. Every time it makes changes it can be reverted to the state at previous prompts. Use git liberally.

I'm just a dumb farmer who quit programming 20 years ago, and I use it to build stuff that works IRL for my operation constantly. A dev should be able to wrap their head around it.

Reply on news.ycombinator.com