"There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper so I barely even touch the keyboard. I ask for the dumbest things like "decrease the padding on the sidebar by half" because I'm too lazy to find it. I "Accept All" always, I don't read the diffs anymore."
"When I get error messages I just copy paste them in with no comment, usually that fixes it. The code grows beyond my usual comprehension, I'd have to really read through it for a while. Sometimes the LLMs can't fix a bug so I just work around it or ask for random changes until it goes away. It's not too bad for throwaway weekend projects, but still quite amusing. I'm building a project or webapp, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works."
""Mostly works" is not a glowing recommendation, and applying vibe coding to serious projects presents serious risks, including the creation of hidden bugs that will bite you later. It's folly. It also inevitably creates technical debt."
Vibe coding relies on giving instructions to LLM-based tools and accepting generated changes without reviewing diffs or fully understanding the resulting code. It often involves copying error messages back into the system and iterating until issues disappear, even if the underlying bug is not truly fixed. This approach can work for throwaway weekend projects, but it carries serious risks for real work. Hidden bugs can be introduced and later surface, while repeated shortcuts accumulate technical debt. A more systematic approach to building with AI agents is presented as a safer alternative, emphasizing structure and process over informal, hands-off iteration.
Read at InfoWorld
Unable to calculate read time
Collection
[
|
...
]