I don't get to code much these days, so I mostly use chatGPT to get occasional helps with scripts and whatnot. I've tried to get help from ChatGPT on a simple javascript/website project that is basically a css/js/html file, but I feel like I don't know how to give the chatbot the code except just pasting it in the prompt. Is Claude better for that, like does it have some IDE or something to play with? Or do people generally use some third party tool for integrations.
I've been using Claude Code for a couple of days
21–30 of 507 posts
Re: I've been using Claude Code for a couple of days
#22I must be the dumbest "prompt engineer" ever, each time I ask an AI to fix or even worse, create something from scratch it rarely returns the right answer and when asked for modification it will struggle even more. All the incredible performance and success stories always come from these Twitter posts, I do find value in asking simple but tedious task like a small refactor or generate commands, but this "AI takes the…
Can you clarify what tools and programming language you use? If find that the issue often is wrong tooling, exotic programming languages or frameworks.
I would consider frontend tasks using Typescript and React quite standard.
Re: I've been using Claude Code for a couple of days
#23I find cline to be incredible about 80% of the time for creating new concept websites or python scripts. I use it with Open router and choose Claude exclusively. I’d CC is the next step we are headed in a crazy and scary direction.
Re: I've been using Claude Code for a couple of days
#24Earlier quoted context omitted.
I was confused untill I watched a video of it in use, nope it wasn't that sarcastic. https://youtu.be/W13MloZg03Y
That guy leads in with stating that he is missing "autocomplete" in claude code. Cleary a misunderstanding of the scope.
I mostly posted the video because I thought it was a good demonstration of the prompts to approve/cost that the tweet was talking about.
He talks about it later of using autocomplete vs complete writing, I don't think he misunderstood the scope just talking about the difference of ways ai can be used for coding assistant.
Re: I've been using Claude Code for a couple of days
#25Sidenote: thank you for using twitter dot com instead of x. This is a little detail and I'm sure I'm not the only one appreciating it.
Re: I've been using Claude Code for a couple of days
#26I must be the dumbest "prompt engineer" ever, each time I ask an AI to fix or even worse, create something from scratch it rarely returns the right answer and when asked for modification it will struggle even more. All the incredible performance and success stories always come from these Twitter posts, I do find value in asking simple but tedious task like a small refactor or generate commands, but this "AI takes the…
I think it's probably the difference between "code" and "programming". An LLM can produce code and if you're willing to surrender to the LLMs version of whatever it is you ask for, then you can have a great and productive time. If you're opinionated about programming, LLMs fall short. Most people (software engineers, developers, whatever) are not "programmers" they're "coders" which is why they have a positive impression of LLMs: they produce code, LLMs produce code... so LLMs can do a lot of their work for them.
Coders used to be more productive by using libraries (e.g: don't write your own function for finding the intersection of arrays, use intersection from Lodash) whereas now libraries have been replaced by LLMs. Programmers laughed at the absurdity of left-pad[1] ("why use a dependency for 16 lines of code?") whereas coders thought left-pad was great ("why write 16 lines of code myself?").
If you think about code as a means to an end, and focus on the end, you'll get much closer to the magical experience you see spoken about on Twitter, because their acceptance criteria is "good enough" not "right". Of course, if you're a programmer who cares about the artistry of programming, that feels like a betrayal.
Re: I've been using Claude Code for a couple of days
#27I must be the dumbest "prompt engineer" ever, each time I ask an AI to fix or even worse, create something from scratch it rarely returns the right answer and when asked for modification it will struggle even more. All the incredible performance and success stories always come from these Twitter posts, I do find value in asking simple but tedious task like a small refactor or generate commands, but this "AI takes the…
I have the same experience. Where AI shines for me is as a form of a semantic search engine or even a tutor of sorts. I can ask for the information that I need in a relatively complex way, and more often than not it will give me a decent summary and a list of "directions" to follow-up on. If anything, it'll give me proper technical terms, that I can feed into a traditional search engine for more info. But that's neve…
Yeah I have had some "magic" moments where I knew "what" I needed, had an idea of "how it would look",but no idea how to do it and ai helped me understand how I should do it instead of the hacky very stupid way I would have done it
Re: I've been using Claude Code for a couple of days
#28I must be the dumbest "prompt engineer" ever, each time I ask an AI to fix or even worse, create something from scratch it rarely returns the right answer and when asked for modification it will struggle even more. All the incredible performance and success stories always come from these Twitter posts, I do find value in asking simple but tedious task like a small refactor or generate commands, but this "AI takes the…
I have the same experience. Where AI shines for me is as a form of a semantic search engine or even a tutor of sorts. I can ask for the information that I need in a relatively complex way, and more often than not it will give me a decent summary and a list of "directions" to follow-up on. If anything, it'll give me proper technical terms, that I can feed into a traditional search engine for more info. But that's neve…
Exactly same experience: since the early-access GPT-3 days, I played out various scenarios, and the most useful case has always been to use generativeAI as semantic search. It's generative features are just lacking in quality (for anything other than a toy project), and the main issues since the early GPT days remains, even though it gets better, it's still too unreliable for (mid-complex systems) serious work. Also, if you don't pay attention, it messes up other parts of the code.
Re: I've been using Claude Code for a couple of days
#29I must be the dumbest "prompt engineer" ever, each time I ask an AI to fix or even worse, create something from scratch it rarely returns the right answer and when asked for modification it will struggle even more. All the incredible performance and success stories always come from these Twitter posts, I do find value in asking simple but tedious task like a small refactor or generate commands, but this "AI takes the…
Maybe it’s the shot up plane effect; we only see the winners but rarely see the failures. Leads us to wrong or incorrect conclusions.
Finding the right prompt to have current generation AI create the magic depicted in twitter posts may be a harder problem than most anticipate.
Re: I've been using Claude Code for a couple of days
#30I must be the dumbest "prompt engineer" ever, each time I ask an AI to fix or even worse, create something from scratch it rarely returns the right answer and when asked for modification it will struggle even more. All the incredible performance and success stories always come from these Twitter posts, I do find value in asking simple but tedious task like a small refactor or generate commands, but this "AI takes the…
You have to learn and figure out how to prompt it. My experience with Claude Code is this: one time it produces an incredible result; another time it's an utter failure. There are prompt tips and tricks which have enormous influence on the end result.