Earlier quoted context omitted.
What, someone cannot utter an opinion anymore?
I find that question ironic.
But isn't that the point?
I've been using Claude Code for a couple of days
221–230 of 507 posts
Re: I've been using Claude Code for a couple of days
#222Are there any videos showing these very advanced use cases? I'd be interested in learning how to achieve this level of proficiency. At the moment I still feel I'm better off without ai
Claude code doesn’t need magic prompts. It’s not perfect but holy moly is it good, when it’s working it just one shots things for you. It’s just EXPENSIVE. I’ve spent 30$ in tokens on it this week. Cursor’s “chat with your codebase” is a funny joke compared to Claude Code. Ask it questions, have it figure things out. I had it analyze the openAPI schema and the backend that is serving the schema for the API I’m writin…
> Claude code doesn’t need magic prompts. It’s not perfect but holy moly is it good, when it’s working it just one shots things for you. It’s just EXPENSIVE. I’ve spent 30$ in tokens on it this week.
As long as it costs less than a developer, it will be used instead of the said developer.
Re: I've been using Claude Code for a couple of days
#223Earlier quoted context omitted.
I decided to try seriously the Sonnet 3.7. I started with a simple prompt on claude.ai ("Do you know claude code ? Can you do a simple implementation for me ?"). After minimal tweaking from me, it gave me this : https://gist.github.com/sloonz/3eb7d7582c33e95f2b000a0920016... After interacting with this tool, I decided it would be nice if the tool could edit itself, so I asked (him ? it ?) to create its next version.…
So you’re telling me you spent 20 dollars and an entire day for 200 lines of JavaScript and 75 lines of python and this to you constitutes a working re-creation of Claude Code? This is why expectations are all out of whack.
2200 lines. Half of them unit tests I would probably have been too lazy to write myself even for a "more real" project. Yes, I consider $20 cheap for that, considering:
1. It’s a learning experience 2. Looking at the chat transcripts, many of those dollars are burned for stupid reasons (Claude often fails with the insertLines/replaceLines functions and break files due to miss-by-1 offset) that are probably fixable 3. Remember that Claude started from a really rudimentary base with few tools — the bootstrapping was especially inefficient
Next experiment will be on an existing codebase, but that’s probably for next weekend.
Re: I've been using Claude Code for a couple of days
#224Earlier quoted context omitted.
So you’re telling me you spent 20 dollars and an entire day for 200 lines of JavaScript and 75 lines of python and this to you constitutes a working re-creation of Claude Code? This is why expectations are all out of whack.
That amount of output is comparable to what many professional engineers produce in a given day, and they are a lot more expensive. Keep in mind this is the commenters first attempt. And I'm surprised he paid so much. Using Aider and Sonnet I've on multiple occasions produced 100+ lines of code in 1-2 hours, for under $2. Most of that time is hunting down one bug it couldn't fix by itself (reflective of real world pro…
Remember that input tokens are quadratic with the length of the conversation, since you re-upload the n previous messages to get the (n+1)-nth message. When Claude completes a task in 3-4 shots, that’s cents. When he goes down in a rabbit hole, however…
Re: I've been using Claude Code for a couple of days
#225A single tweet with lots of analogy, with no screenshot/screen recording/code examples whatsoever. These are just words. Are we just discussing programming based on vibe?
I think the interest has more to do with who is doing the tweeting, don't you think?
Re: I've been using Claude Code for a couple of days
#226Does anyone know a good video of someone demonstrating their workflow with these coding assistants?
I have written a whole project [1] for making amateur videoclips [2] of A.I. generated music, using GPT and other LLMs. 10.000 to 12.000 lines of code was written exclusively by AIs.
I didn't know at the start what should be done, and the code ended up having lots of duplication, but i refactored it a lot and now it is in the order of 4.000 lines.
I could make some screencasts about the development process, but it is very simple. I ask it to write some code, and I always provide some relevant context. When it is a method of a struct, i give it the struct, and/or a similar method, and i describe what i want the method to do. Also sometimes I give it the type signature of the method/function which has to write. When it has to return an error, i provide the error Enum.
In other words, by providing the context, i never use it zero shot, rather always aim for few shot answers. When i want another function to use, i just provide the type signature, and almost never the whole function.
One more detail, I give as minimal of a context as possible. I use as a context window, 100 tokens, 200 or maximum 300 tokens. 100 tokens per query, then delete the context for the next task, and provide new context. Never use more than few hundred tokens per query. Even 300 tokens is pushing it too far.
That's about it! Never use LLMs zero shot, always few shot, and never use more than 100 tokens per query.
[1] https://github.com/pramatias/fxp_videoclipper/tree/main [2] https://www.youtube.com/watch?v=RmmoMPu091Y
Re: I've been using Claude Code for a couple of days
#227Earlier quoted context omitted.
If you already have a moderately complex code base it starts making mistakes.
Depends a lot on what context you feed it. If you have decent internal documentation and can feed it the right files, it tends to do quite well for me, often needing corrections or style fixes. To use it most effectively, you have to know the vast majority of the code that you want it to write ahead of time. It saves time typing, looking up methods, wrangling APIs appropriately, and sometimes it surprises me by worki…
I think the next step is to get it to run some automated testing against the code it produces and then fix issues accordingly.
If I was a better programmer I'd be working on that solution right now.
Re: I've been using Claude Code for a couple of days
#228I've been using Claude for about 3 months now. What I've learned is that you have to learn how Claude "thinks" about your project, meaning what kinds of mistakes he makes. They're pretty consistent. As you uncover each new kind, compile a list of things to remind him of each time. For my own project, some of my reminder items to give him each chat (sometimes multiple times in the chat) include: "maintain a single source of truth", "avoid duplication", "stick to our established architecture instead of building new architecture". I always make sure he has an up-to-date file tree to look at. I remind him to ask me if there's a particular file he needs to see for reference instead of making up something new. I also say to make the changes specific to just what needs to be changed, rather than building in stuff and "anticipating" problems that aren't even here yet. Stuff like that. By the way, Project Knowledge is a very useful feature. Just don't expect Claude to ever look at it after your first statement/question. That's when he looks at what's there.
Re: I've been using Claude Code for a couple of days
#229Earlier quoted context omitted.
What I've noticed from my extensive use over the past couple weeks has been Claude Code really sucks at thinking things through enough to understand the second and third order consequences of the code that it's writing. That said, it's easy enough to work around its deficiencies by using a model with extended thinking (Grok, GPT4.5, Sonnet 3.7 in thinking mode) to write prompts for it and use Claude Code as basically…
"Claude Code really sucks at thinking things through enough to understand the second and third order consequences of the code that it's writing" Yup, that's our job as software engineers.
> Yup, that's our job as software engineers
The more seasoned you are as a SWE, the higher the orders you consider, and not just on the technical aspect, but the human and business sides as well.
Re: I've been using Claude Code for a couple of days
#230I've been using Claude for about 3 months now. What I've learned is that you have to learn how Claude "thinks" about your project, meaning what kinds of mistakes he makes. They're pretty consistent. As you uncover each new kind, compile a list of things to remind him of each time. For my own project, some of my reminder items to give him each chat (sometimes multiple times in the chat) include: "maintain a single sou…
Tangential but referring to the AI as anything other than "it" is still extremely uncomfortable to me. It feels like the first step towards an inevitable "AI girl/boyfriend" trap.