Live data from Hacker News

Ask HN: Why is my Claude experience so bad? What am I doing wrong?

news.ycombinator.com

121–125 of 125 posts

Re: Ask HN: Why is my Claude experience so bad? What am I doing wrong?

#121
Not so experienced with Claude Code, but the web version does the job for me. I mean, I don't create very complex stuff for others (mostly websites and simple apps) but it did some things that I am proud of (I'm not a dev - have some exp with python, but even that is really basic stuff. So, here's what I do (makes it really easy to do stuff (at least simple stuff I do): - Start a new project and discuss every single detail about it with Claude. - Tell it to write a txt or pdf summary of everything and place that file in project knowledge. - After that tell it to give you a complete project structure and create it - Then simply start populating the files. - Place each file in your project knowledge so it can see it After this it's just debugging which mostly goes smooth as well

I've been playing with it for almost two years now, and this is what gets me there. ChatGPT never got even close to it.

Re: Ask HN: Why is my Claude experience so bad? What am I doing wrong?

#122
post #33

The truth is that there is a lot of hype. You need to be reasonably experienced and guide it. First, you need to know that Claude will create nonsensical code. On a macro level it's not exactly smart it just has a lot of contextual static knowledge. Debugging is not it's strongest skill. Most models don't do good at all. Opus is able to one-shot "troubleshooting" prompts occasionally, but it's a high probability that…

I use AI-Lint to enforce basic code hygeine and design taste across languages, and force it to develop test iterations it can run on its own and tell it to iterate until the tests go green.

https://ai-lint.dosaygo.com

Re: Ask HN: Why is my Claude experience so bad? What am I doing wrong?

#123
post #33

The truth is that there is a lot of hype. You need to be reasonably experienced and guide it. First, you need to know that Claude will create nonsensical code. On a macro level it's not exactly smart it just has a lot of contextual static knowledge. Debugging is not it's strongest skill. Most models don't do good at all. Opus is able to one-shot "troubleshooting" prompts occasionally, but it's a high probability that…

Am I crazy thinking that interacting with such a system is a nightmarishly frustrating way to write code? Like trying to write with a wet noodle - always off in some way. Write the code feels way more precise and not less efficient.

This has been my experience as well. I get drained at the end, and I spent most of my energy and thinking capacity dealing with the LLM instead of the problem space.

Re: Ask HN: Why is my Claude experience so bad? What am I doing wrong?

#125
I used this entire HN discussion as the input to a design/task SKILL.md. I asked Claude to prepare the design document and a task list. When it was done, I asked it to implement the task list.

I got this: https://github.com/hughdbrown/visualize-grid-layouts.git

You can follow how this all happened by looking in `docs/design/`.

The SKILL.md had this description:

``` Collaboratively designs a new software feature with the developer. Explores the existing codebase to ground all technical decisions in the project's actual architecture, conventions, and dependencies. Produces two deliverables:

1. *Product Requirements Document (PRD)* — what the feature does, technical decisions, how it operates, and ordered implementation stages.

2. *Detailed Task List* — within each stage, test-first scoped steps covering tests to write, code to implement, config changes, environment variables, dependencies, and documentation.

Both deliverables are written to files in the project for reference during implementation. ```

You can get Claude to produce the skill for you, too.

Post reply on HN