301–310 of 322 posts
I don't get it. The title says "What makes Claude Code so damn good", which implies that they will show how Claude Code is better than other tools, or just better in general. But they go about repeating the Claude Code documentation using different wording. Am I missing something here? Or is this just Anthropic shilling?
Can i shill my business on here too or will it get canned because i'm a nobody?
Earlier quoted context omitted.
https://gist.github.com/githubcustomerserviceistrash/c716e76... I should mention I made that one for my research/stats workflow, so there's some specific stuff in there for that, but you can prompt chat gpt to generalize it.
I mean, damn. Are terms like “executable oracles” and “hermetic boots” related to your domain, or are you using these as terms of art for an agent? Oracle being a source of truth, hermetic meaning no external dependencies or side effects - definitions in furtherance of your request for concise language. Would love to understand more.
> - IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked
> - VERY IMPORTANT: You MUST avoid using search commands like `find` and `grep`.
Does using caps, or the stars, really carry meaning through the tokenization process?
Earlier quoted context omitted.
If you aren’t using a client that automatically uses the context of your repos then you don’t understand why people like Claude. You need to use the Claude Code CLI in order to really get the best results.
I’m not in the market for a solution where I need to trust some company with my IP. I understand that Claude also wants to serve my use case, so I take these headlines at face value as also applying to me, since they don’t qualify themselves with ‘Claude Code CLI’.
Earlier quoted context omitted.
> I've literally built the entire MVP of my startup on Claude Code and now have paying customers. Would you mind linking to your startup? I’m genuinely curious to see it. (I won’t reply back with opinions about it. I just want to know what people are actually building with these tools!)
He won’t, everyone that says they made a profitable startup with some AI code generator 3000 never seems to link their startup. Interesting.
1. I code with LLMs (Copilot, Claude Code). Like anyone who has done so, I know a lot about where these tools are useful and where they're hopeless. They can't do it all, claims to the contrary aside.
2. I've built a couple businesses (and failed tragicomically at building a couple more). Like anyone who has done so, I know the hard parts of startups are rarely the tech itself: sales, marketing, building a team with values, actually listening to customers and responding to their needs, making forward progress in a sea of uncertainty, getting anyone to care at all... sheesh, those are hard! Last I checked, AI doesn't singlehandedly solve any of that.
Which is not to say LLMs are useless; on the contrary, used well and aimed at the right tasks, my experience is that they can be real accelerants. They've undoubtedly changed the way I approach my own new projects. But "LLMs did it all and I've got a profitable startup"... I mean, if that's true, link to it because we should all be celebrating the achievement.
I made insane progress with CC over last several weeks, but lately have noticed progress stalling. I’m in the middle of some refactoring/bug fixing/optimization but it’s constantly running into issues, making half baked changes, not able to fix regressions etc. Still trying to figure out how to make do a better job. Might have to break it into smaller chunks or something. Been pretty frustrating couple of weeks. If a…
Earlier quoted context omitted.
Right-- it's only really capable of trivial code and boilerplate, which I usually just copy from one of my older programs, examples in docs, or a highly-ranked recent SO answer. Saves me from having to converse with an expensive chatbot, and I don't have to worry about random hallucinations. If it's a new, non-trivial algorithm, I enjoy writing it.
For me, it's a lot easier getting the LLM to do it than browsing through multiple SO answers, or even finding some old code of mine. Oh, and the chatbot is cheap. I pay for API usage. On average I'm paying less than $5 per month. > and I don't have to worry about random hallucinations. For boilerplate code, I don't think I've ever had to fix anything. It's always worked the first time. If it didn't, my prompt was at…
Earlier quoted context omitted.
Bugs, yes. Security vulnerabilities? Rarely enough that it wouldn’t make my HN list. It’s not remotely hard to avoid the most common issues.
Granted I've only been using Claude for a short time, but in my experience it tends to write code that matches the style of the code it's editing. Which is sort of a "no duh" thing in retrospect but I hadn't considered that. That is to say old crappy code I wrote long ago when I was dumber gets old-crappy dumber code style suggestions from Claude. And newer better-practices code that is very careful gets Claude to fo…
Earlier quoted context omitted.
I’m not in the market for a solution where I need to trust some company with my IP. I understand that Claude also wants to serve my use case, so I take these headlines at face value as also applying to me, since they don’t qualify themselves with ‘Claude Code CLI’.
‘Claude Code’ refers to the CLI.
Earlier quoted context omitted.
Granted I've only been using Claude for a short time, but in my experience it tends to write code that matches the style of the code it's editing. Which is sort of a "no duh" thing in retrospect but I hadn't considered that. That is to say old crappy code I wrote long ago when I was dumber gets old-crappy dumber code style suggestions from Claude. And newer better-practices code that is very careful gets Claude to fo…
Thanks for sharing; that sounds rather reasonable. But I was under the impression that this new "vibe coding" thing was where you start with a "clean slate" altogether (the llm itself generates/picks the "initial state" in terms of idiomatic or not-so-idiomatic handling of whatever conditions rather than copying it from existing code)?
Overall "meta" commands seem to work much more effectively that I expected. I'm still getting used to it and letting it run more freely lately but there's some sort of a loop you can watch as it runs where it will propose code given logic that is dumb and makes you want to stop it and intervene... but on the next step it evaluates what it just wrote and rejects for the same reason I would have rejected it and then tries something else. It's somewhat interesting to watch.
If you asked a new "I need you to write XYZ stat!" vs "We care a lot about security, maintainability and best practices. Create a project that XYZ." you would expect different product from the new hire. At least that's how I am treating it.
Basically I would give it a sort of job description. And you can even do things like pick a project you like as a model and have it write a file describing development practices used in that project. Then in the new project ask it to refer to that file as guidance and design a plan for writing the program. And then let it implement that plan. That would probably give a good scaffold, but I haven't tried. It seems like how I would approach that right now as an experiment. It's all speculation but I can see how it might work.
Maybe I'll get there and try that, but at the moment I'm just doing things I have wanted to do forever but that represented massive amounts of my time that I couldn't justify. I'm still learning to trust it and my projects are not large. Also I am not primarily a programmer (physicist who builds integrations, new workflows and tools for qc and data handling at a hospital).