Coté

Eight years of wanting, three months of building with AI lalitm.com/post/buil…

When I was working on something where I didn’t even know what I wanted, AI was somewhere between unhelpful and harmful. The architecture of the project was the clearest case: I spent weeks in the early days following AI down dead ends, exploring designs that felt productive in the moment but collapsed under scrutiny. In hindsight, I have to wonder if it would have been faster just thinking it through without AI in the loop at all.

And:

The addiction

There’s an uncomfortable parallel between using AI coding tools and playing slot machines28. You send a prompt, wait, and either get something great or something useless. I found myself up late at night wanting to do “just one more prompt,” constantly trying AI just to see what would happen even when I knew it probably wouldn’t work. The sunk cost fallacy kicked in too: I’d keep at it even in tasks it was clearly ill-suited for, telling myself “maybe if I phrase it differently this time.”

The tiredness feedback loop made it worse29. When I had energy, I could write precise, well-scoped prompts and be genuinely productive. But when I was tired, my prompts became vague, the output got worse, and I’d try again, getting more tired in the process. In these cases, AI was probably slower than just implementing something myself, but it was too hard to break out of the loop.

Which is to say, from another:

Vibe coding is when it’s 1am, everyone else in the house is asleep, you’ve got your favourite drink and your favourite music playing while you goof around writing some code in your favourite language or trying out a new language just because you love learning new stuff while chatting to cool people also chilling out late at night indulging on whatever hobby makes them happy.