TheGuySwann on nostr

Open in Damus

@TheGuySwann 1747318168

The biggest annoyance of “vibe coding” with ChatGPT is its incessant need to write an entire application every single time you ask it anything, when it becomes a mess of bugs and contradictions with even modest size.

Trying to get the damn thing to modularize each component and put them together coherently is something I have to explain over and over again. It just wants to write 1,000 lines of code every time even though it constantly fails at it 🤣

Anyone found the magic sauce LLM that actually already works this way and knows to keep things in small components by default?

632❤️10🤙4😑1🥲1

⚡A C V⚡ · 52w

outline and planning. chatgpt needs all your requirements well documented, you can't just start asking for shit, its gonna make up what it hasn't been told is your goal. Typically devs don't plan because they have to learn the plan as they develop the real requirements as they go along. llms wor...

I feel this so much. Occasionally the thing will lose all context and you end up with duplicate files, random weird folder structures and files that don’t have any consistency to them. I have yet to figure out how to make it do as I ask.

⚡A C V⚡ · 52w

also, chatgpt seems to give me 1000 words no matter what its always 1200 words or less

Galaxie 5000 · 52w

I’ve had better luck with nostr:npub17304velluajf6lylvjynpj2f3ndg396w063gj2gef5qk0nwtcyjqfj9yky and the Deep Seek model. But I only use it for very simple coding (not a coder).

Sid Phrase · 52w

Have you tried Replit? I just started experimenting there. It writes the codes in sections and you can revert back to prior milestones in the project. I used ChatGPT to build my initial prompt for Replit.

Don’t use chatGPT, for one… Second, use an IDE like windsurf Third, you should highlight code or mention files you want adjusted, then explicitly write what actions you want it to take. Your prompt is the most important part. Also, reject code and tell it that it fucked up, and try again

Jon Matcho · 52w

Still looking to tame all of this in Visual Studio. I've been treading lightly but am optimistic it WILL happen, but doubtful it's available now.

I’ve found it necessary to ask very specific questions regarding atomic pieces of functionality; “write a typescript function that does X.” And then a few follow up iterations usually gets me within spitting distance of what I’m looking for. Raycast has some useful prompts for code question...

Us o3 in ask mode to plan the stuff out, then use gemeni 2.5 to implement . If your using cursor flip buttons and switches to widen chat context, setup auto-run and enable mcp tool use. Create project rules to limit hallucinations, create a custom agent to limit hallucinations, and create an agent ...

as others have suggested use an agent based ide as cursor/windsurf/vcode cursor out of the box gives you decent performance, if you wanna go deep vcode+roo is a deep rabbit hole specially if you dig into advanced setups like the SEC playbook https://github.com/jodobear/sparcaroo

Sounds to me like it's trying to be independent.

ChipTuner · 52w

Cline w/claude, Cursor, or copilot agents. There are probably better answers for how this works, but with copilot agents it breaks work down into small pieces and feeds it back to the LLM so it itterates on smaller components isntead of trying to do the job all at once. In lay terms: I think the mod...

TheBitcoinManual · 52w

Lol vibe coding, because we had such a shortage of technical debt on any web application already

First assess problem. Break down tasks Architect solution first. Define spec. Implement to the spec. When instructing for modularity, focus on input, output expectations not the 30000 ft view

Bill Cypher · 52w

Design is separate from writing code. When writing code ask it explicitly for single functions with specific inputs and outputs. Write a function called fun that takes inputs x, and y. Does blah, and outputs z.

Did you try Roo code with the nostr addons? https://github.com/jodobear/sparcaroo

₿oniz23⚡️🏴‍☠️🇮🇹 · 52w

Code writing I think we are still 10 years behind before AI can partially replace developers

SovereignArab · 52w

No idea what works well with medium+ size. Pretty much you need to be very specific and still it struggles.

Just prompt for it not doing that.

Dustin Dannenhauer · 52w

Cline (open source vs code extension)

nostr:nevent1qqstlrf4qdmnqg5zu72eklk0pv2tdz7n6plmd3lr5w6j6t2wxu38gfgpz9mhxue69uhkummnw3ezuamfdejj7q3qwqfzz2p880wq0tumuae9lfwyhs8uz35xd0kr34zrvrwyh3kvrzusxpqqqqqqzfxp00r