ruburi
@ruburi
ok i can conclude my late night coding session today with this statement: either i suck at prompting, or claude code cant do anything that goes slightly above junior level development im kinda scared to leave a codebase to llms. i understand that maybe i dont use its full power, but im not a beginner in prompt engineering and try to write instructions as clearly as possible, involve opus to write comprehensive architecture plans etc -> still hard to follow basic logical principles. as long as there is no agi (logic) -> codebases can be easily messed up. even when im considering leaving the agent to do simple tasks like cleaning up some code, it can forget functions it wrote a minute ago or start overcomplicating things that said, i will proceed making the mini app without using claude code or copilots. i find llms extremely useful when learning new information quickly or summarizing concepts -> must have ps: spent $200 on api calls. maybe not much, but it gave me a good understanding of how things really work. yeah might go at a slower pace, but steady
2 replies
2 recasts
14 reactions
ruburi
@ruburi
ah yeah and also i figured out that i hate watching someone work, constantly correcting or monitoring them, standing over someone while they work -> no thanks, leave people alone (you cant leave llm alone) so basically me staring at token output stream and waiting for another mess -> didnt like the experience. i dont know how people here are vibecoding things this way. oh also, forgot to mention that the architectural art in the codebase disappears when llms get involved. structures end up being quite similar to each other
0 reply
0 recast
1 reaction