AI vibe coding is the “next level” for experienced programmers. This phrase coined by OpenAI co-founder Andrej Karpathy describes a state of “flow” in using AI tools in the software development process. This CEX topic aims at testing the potential and the limits for this approach, by designing a well-researched self-experiment amongst ourselves.
The original X post by Karpathy reads like this:
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.
In short: You should explore if and how AI Vibe Coding really works.
The team working on this topic should clarify the research question and organize an in-depth trial amongst the team.
Optional: If it works out, a try-out-event with the whole CEX course (all of us trying a 1-hour-Vibe-Coding session, and then comparing the results) would be great. But this may be too complex to organize, so it is strictly nice-to-have.