[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
Settings Mobile Home
/g/ - Technology


Thread archived.
You cannot reply anymore.


[Advertise on 4chan]


File: memory-magritte.jpg (33 KB, 484x600)
33 KB JPG
If you use AI to generate code from your pseudocode, is it still vibecoding?
>>
>>109602921
Is using AI to do a language translation vibecoding?
If your answer yes to that, then you know the answer.
>>
>>109602967
Counterpoint: bun
>>
vibecoding is mainly defined by not reviewing the output.
that said, with pure translation, much less review is needed, so it helps
>>
>>109603171
Counterpoint: bun
>>
>>109602921
I'd say yes. Pseudocode can be as imprecise as natural language. It also allows you to skip as many details as natural language.
If your pseudocode is actually as precise as a programming language, it basically becomes it's own programming language. But at that point, you would be better off implementing the algorithm in python, since that would give you an executable artifact.
>>
>>109602921
vibecoding is telling an llm to implement an idea without giving it any technical guidance, hoping it will do it, but without any expectations
if you know what you want to get out of it, it's "ai-assisted development"
>>
>>109605550
It's just another layer of abstraction.
What if you feed it a double sum math formula that you wrote for a specific problem and ask it translate it to Python and then review it.



[Advertise on 4chan]

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.