How can I improve my use of AI in programming?

Consider giving Cursor a try. I personally like the entire UI/UX, their agent has good context, and the entire experience overall is just great. The team has done a phenomenal job. Your workflow could look something like this:

1. Prompt the agent

2. The agent gets too work

3. Review the changes

4. Repeat

This can speed up your process significantly, and the UI clearly shows the changes + some other cool features

First you have to be very specific with what you mean by idiomatic code - what’s idiomatic for you is not idiomatic for an LLM. Personally I would approach it like this: 1) Thoroughly define step-by-step what you deem to be the code convention/style you want to adhere to and steps on how you (it) should approach the task. Do not reference entire files like “produce it like this file”, it’s too broad. The document should include simple small examples of “Good” and “Bad” idiomatic code as you deem it. The smaller the initial step-by-step guide and code conventions the better, context is king with LLMs and you need to give it just enough context to work with but not enough it causes confusion.

2) Feed it to Opus 4.5 in planning mode and ask it to follow up with any questions or gaps and have it produce a final implementation plan.md. Review this, tweak it, remove any fluff and get it down to bare bones.

3) Run the plan.md through a fresh Agentic session and see what the output is like. Where it’s not quite correct add those clarifications and guardrails into the original plan.md and go again with step 3.

What I absolutely would NOT do is ask for fixes or changes if it does not one-shot it after the first go. I would revise plan.md to get it into a state where it gets you 99% of the way there in the first go and just do final cleanup by hand. You will bang your head against the wall attempting to guide it like you would a junior developer (at least for something like this).

I've been heavily vibe coding for a couple of personal projects. A free kids typing game and bringing back a multiplayer game I played a lot as a kid back to life both with pretty good success.

Things I personally find work well.

1. Chat through with the AI first the feature you want to build. In codex using vscode I always switch to chat mode, talk through what I am trying to achieve and then once myself and the AI are in "agreement" switch to agent mode. Google's antigravity sort of does this by default and I think it's probably the correct paradigm to use.

2. Get the basics right first. It's easy for the AI to produce a load of slop, but using my experience of development I feel I am (sort of) able to guide the AI in advance in a similar way to how I would coach junior developers.

3. Get the AI to write tests first. BDD seems to work really well for AI. The multiplayer game I was building seemed to regress frequently with just unit tests alone, but when I threw cucumber into the mix things suddenly got a lot more stable.

4. Practice, the more I use AI the more I believe prompting is a skill in itself. It takes time to learn how to get the best out of an Agent.

What I love about AI is the time it gives me to create these things. I'd never been able to do this before and I find it very rewarding seeing my "work" being used by my kids and fellow nostalgia driven gamers.

I break everything down into very small tasks. Always ask it to plan how it will do it. Make sure to review the plan and spot mistakes. Then only ask it to do one step at a time so you can control the whole process. This workflow works well enough as long as you're not trying to do anything too interesting. Anything which is even a little bit unique it fails to do very well.

I see LLMs as searchers with the ability to change the data a little and stay in a valid space. If you think of them like searchers, it becomes automatic to make the search easy (small context, small precise questions), and you won't keep trying again and again if the code isn't working(no data in the training). Also, you will realize that if a language is not well represented in the training data, they may not work well.

The more specific and concise you are, the easier it will be for the searcher. Also, the less modification, the better, because the more you try to move away from the data in the training set, the higher the probability of errors.

I would do it like this:

1. Open the project in Zed 2. Add the Gemini CLI, Qwen code, or Claude to the agent system (use Gemini or Qwen if you want to do it for free, or Claude if you want to pay for it) 3. Ask it to correct a file (if the files are huge, it might be better to split them first) 4. Test if it works 5. If not, try feeding the file and the request to Grok or Gemini 3 Chat 6. If nothing works, do it manually

If instead you want to start something new, one-shot prompting can work pretty well, even for large tasks, if the data is in the training set. Ultimately, I see LLMs as a way to legally copy the code of other coders more than anything else

Using voice transcription is nice for fully expressing what you want, so the model doesn't need to make guesses. I'm often voicing 500-word prompts. If you talk in a winding way that looks awkward when in text, that's fine. The model will almost certainly be able to tell what you mean. Using voice-to-text is my biggest suggestion for people who want to use AI for programming

You can also ask it, "do you have any questions?" I find that saying "if you have any questions, ask me, otherwise go ahead and build this" rarely produces questions for me. However, if I say "Make a plan and ask me any questions you may have" then it usually has a few questions

I've also found a lot of success when I tell Claude Code to emulate on some specific piece of code I've previously written, either within the same project or something I've pasted in

Here’s how I would do this task with cursor, especially if there are more routes.

I would open a chat and refactor the template together with cursor: I would tell it what I want and if I don’t like something, I would help it to understand what I like and why. Do this for one route and when you are ready, ask cursor to write a rules file based on the current chat that includes the examples that you wanted to change and some rationale as to why you wanted it that way.

Then in the next route, you can basically just say refactor and that’s it.

How did you learn how to use AI for coding? I'm open to the idea that a lot of "software carpentry" tasks (moving/renaming files, basic data analysis, etc) can be done with AI to free up time for higher level analysis, but I have no idea where to begin -- my focus many years ago was privacy, so I lean towards doing everything locally or hosted on a server I control so I lack a lot of knowledge of "the cloud" my HN betheren have.

Ask people to do things for you. Then you will learn how to work with something/someone who has faults but can overall be useful if you know how to view the interaction.

Hey, Boris from the Claude Code team here. A few tips:

1. If there is anything Claude tends to repeatedly get wrong, not understand, or spend lots of tokens on, put it in your CLAUDE.md. Claude automatically reads this file and it’s a great way to avoid repeating yourself. I add to my team’s CLAUDE.md multiple times a week.

2. Use Plan mode (press shift-tab 2x). Go back and forth with Claude until you like the plan before you let Claude execute. This easily 2-3x’s results for harder tasks.

3. Give the model a way to check its work. For svelte, consider using the Puppeteer MCP server and tell Claude to check its work in the browser. This is another 2-3x.

4. Use Opus 4.5. It’s a step change from Sonnet 4.5 and earlier models.

Hope that helps!

  > I add to my team’s CLAUDE.md multiple times a week.

  ## Code Style (See JULIA_STYLE.md for details)
  - Always use explicit `return` statements
  - Use Float32 for all numeric computations
  - Annotate function return types with `::`
  - All `using` statements go in Main.jl only
  - Use `error()` not empty returns on failure
  - Functions >20 lines need docstrings

  ## Do's and Don'ts
  -  Check for existing implementations first
  -  Prefer editing existing files
  -  Don't add comments unless requested
  -  Don't add imports outside Main.jl
  -  Don't create documentation unless requested

  @AGENTS.md

1. Introduce it to the code base (tell it: we're going to work on this project, project does X is written in language Y). Ask it to look at the project to familiarize.

2. Tell it you want to refactor the code to achieve goal Z. Tell it to take a look and tell you how it will approach this. Consider showing it one example refactor you've already done (before and after).

3. Ask it to refactor one thing (only) and let you look at what it did.

4. Course correct if it didn't do the right thing.

5 Repeat.

Would love to hear any feedback using Google's anitgravity from a clean slate. Holiday shutdown is about to start at my job and I want to tinker with something that I have not even started.

I find Claude Code works best when given a highly specific and scoped tasks. Even then sometimes you'll need to course correct it once you notice its going off course.

Basically a good multiplier, not a replacement. Still requires the user to have good understanding about the codebase.

In addition to what the sibling commenters are saying: Set up guardrails for what you expect in your project's documentation. What is the agent allowed to do when writing unit tests vs say functional tests, what packages it should never use, coding and style templates etc.

I like to followup with "Does this make sense?" or similar. This gets it to restate the problem in its own words, which not only shows you what its understanding of the problem is, it also seems to help reinforce the prompt.

Voice prompts, restate what you want, how you want it from multiple vantage points. Each one is a light cone in a high dimensional space, your answer lies in their intersection.

Use mind altering drugs. Give yourself arbitrary artificial constraints.

Try using it in as many different ridiculous ways you can. I am getting the feeling you are only trying one method.

> I've had a fairly steady process for doing this: look at each route defined in Django, build out my `+page.server.ts`, and then split each major section of the page into a Svelte component with a matching Storybook story. It takes a lot of time to do this, since I have to ensure I'm not just copying the template but rather recreating it in a more idiomatic style.

Relinquish control.

Also, if you have very particular ways of doing things, give it samples of before and after (your fixed output) and why. You can use multishot prompting to train it to get the output you want. Have it machine check the generated output.

> Simple prompting just isn't able to get AI's code quality within 90%

Would simple instructions to a person work? Esp a person trained on everything in the universe? LLMs are clay, you have to mold them into something useful before you can use them.

There are very real limitations on AI coders in their current state. They simply do not produce great code most of the time. I have to review every line that it generates.

I did a similar thing.

put an example in the prompt: this was the original Django file and this is the rewritten in SveltKit version.

the ask it to convert another file using the examples as a template.

you will need to add additional rules for stuff not covered.

or maybe fix a bad try of the agent and add it as a second example

The hack for sveltekit specifically, is to first have Claude translate the existing code into a next.js route with react components. Run it, debug and tweak it. Then have Claude translate the next.js and react components into sveltekit/svelte. Try and keep it in a single file for as long as possible and only split it out once it's working.

I've had very good results with Claude Code using this workflow.