331–340 of 388 posts
Earlier quoted context omitted.
The way I do this is by still writing tests.
Do tests let you understand a codebase you have not written?
To have useful tests, you must write the APIs for the functions, and give examples of how to wire up the various constructs, and correct input/output pairs.
Implementations of those functions that pass the test now have significant constraints that mean you understand a lot about it.
Earlier quoted context omitted.
Do tests let you understand a codebase you have not written?
this desire to understand code will be soon be seen as rather anachronistic. What's important is that you understand your tests. Let the AI generate the code. The spec and the test are your human contribution.
Reading all these glowing reviews of Claude Code, I still get the feeling that either everyone’s been paid off or it’s just the die-hard fans of terminal windows and editors like Emacs and Vim. Using the terminal is right up their alley—it’s in their DNA. Every time I read comments saying Claude Code is far better than Cursor, I fire it up, pay for a subscription, and run it on a large, complex TypeScript codebase. F…
You are absolutely right. A large portion are influencers (I would estimate around 95% of those you see on YouTube and forums) that are full of hype. I think most are not affiliated with Anthropic or any vendor, they are just trying to sell a course, ebook or some "get rich with AI" scheme.
What I appreciate about Claude Code:
- Since it is a terminal/CLI tool it can be run headlessly from cron jobs or scripts. This makes it easy to automate.
- I appreciate the predictable pricing model. A flat monthly fee gives me access to Claude Sonnet and Opus 4 in five-hour sessions each with its own usage limit that resets at the start of a new session. There is a fair use policy of around 50 sessions per month, but I haven’t hit that yet. I deliberately run only one instance at a time as I prefer to use it responsibly unlike some of the "vibe" influencers who seem to push it to the limit.
That's it. Despite being a CLI based tool, Claude Code is remarkably out of the box for what it offers.
That said, no coding agent I have encountered can fully ingest a large inconsistent legacy codebase especially one with mixed architectures that accumulated over years. This limitation is mainly due to context size constraints, but I expect this to improve as context windows grow.
Claude Code is hard to describe. It’s almost like I changed jobs when I started using it. I’ve been all-in with Claude as a workflow tool, but this is literally steroids. If you haven’t tried it, I can’t recommend it enough. It’s the first time it really does feel like working with a junior engineer to me.
Weirdly enough I have the opposite experience where it will take several minutes to do something, then I go in and debug for a while because the app has become fubar, then finally realize it did the whole thing incorrectly and throw it all away. And I reach for Claude quite a bit because if it worked as well for me like everyone here says, that would be amazing. But at best it’ll get a bunch of boilerplate done after…
The quality of the generated code is inversely proportional to the time it take to generate it. If you let Claude Code work alone for more than 300 seconds you will receive garbage code. Take that as a hint, if it can't finish the task in this time it means you are asking too much. Break up your feature and try with a smaller feature.
Reading all these glowing reviews of Claude Code, I still get the feeling that either everyone’s been paid off or it’s just the die-hard fans of terminal windows and editors like Emacs and Vim. Using the terminal is right up their alley—it’s in their DNA. Every time I read comments saying Claude Code is far better than Cursor, I fire it up, pay for a subscription, and run it on a large, complex TypeScript codebase. F…
There must at this point be lots and lots of actual walkthroughs of people coding using Claude Code, or whatever, and producing real world apps or libraries with them right? Would be neat to have a list because this is what I want to read (or watch), rather than people just continuously telling me all this is amazing but not showing me it’s amazing.
I see two trends recently: 1. low skill people using it for trivial projects. 2. devs writing out the whole app into memory/context down to the names of the files, interfaces, technologies, preparing the testing, compilation framework and then hand-holding the llm to arrive (eventually) at an acceptable solution. Example: https://www.youtube.com/watch?v=Y4_YYrIKLac 80% (99%?) of what you hear about llms are from the…
Ah, Stone Soup: https://en.wikipedia.org/wiki/Stone_Soup
Earlier quoted context omitted.
Sigh. As others have commented, over and over again in the last 6 months we've seen discussions on HN with the same basic variation of "Claude Code [or whatever] is amazing" with a reply along the lines of "It doesn't work for me, it just creates a bunch of slop in my codebase." I sympathize with both experiences and have had both. But I think we've reached the point where such posts (both positive and negative) are…
Here's a few general observations. Your LLM (CC) doesn't have your whole codebase in context, so it can run off and make changes without considering that some remote area of the codebase are (subtly?) depending on the part that claude just changed. This can be mitigated to some degree depending on the language and tests in place. The LLM (CC) might identify a bug in the codebase, fix it, and then figure, "Well, my wo…
Then it doesn’t need to feel (or rg) through the whole codebase.
You also use plan mode to figure out the issue, write the implementation plan in a .md file. Clear context, enter act mode and tell it to follow the plan.
Earlier quoted context omitted.
> this sounds like a cop out This may sound more mean than I intend, but your comment is exactly the kind of thing the GP post was describing as useless yet ubiquitous.
i mean i get it, but at some point you have to either assume everyone is lying or we are all bots or something. it's probably the same feeling i get when i read someone having trouble and my first thought is like "they aren't using it right". i'm sure the reverse is something like "they aren't a real programmer" LOL.
Without concrete details about the exact steps you're taking, these conversations are heat without light.
There must at this point be lots and lots of actual walkthroughs of people coding using Claude Code, or whatever, and producing real world apps or libraries with them right? Would be neat to have a list because this is what I want to read (or watch), rather than people just continuously telling me all this is amazing but not showing me it’s amazing.
Besides that, I think your best bet is to find someone on youtube creating something "live" using a LLM. Something like this: https://www.youtube.com/watch?v=NW6PhVdq9R8