[fibonachos]

Multiline autocomplete is still the biggest productivity boost for me. This works well in a familiar codebase with reasonably consistent patterns.

After that it’s the “ask” capability when I need to get oriented in unfamiliar and/or poorly documented code. I can often use the autocomplete pretty effectively once I understand the patterns and naming conventions.

Similarly, agents are good for a first pass triage and plan when troubleshooting tricky bugs.

Still haven’t had a good candidate for going full vibe code. Maybe that’s because I don’t do a lot of greenfield coding outside of work, which seems to be where it shines.

Just my experience. It’s new set of tools in the toolbox, but not always the right one for a given task.

[OptionOfT]

Multiline autocomplete is very disruptive. It's overly verbose, and it constantly pulls me out of my flow, because it's not what I want.

I know what I want before I type it. Having to parse the auto-completion disrupts the thought process of what I _wanted_ to write.

[AstroBen]

I'm working on a greenfield project right now and my experience has been 100% in line with the video

I think it might be even worse for greenfield work, as that's when you're establishing a lot of patterns. You don't want AI to have any role in that

[Garlef]

Yes. And AI is bad at design.

But that's why you tell the AI to refactor.

I've started a greenfield project and went 100% AI for learning purposes (of course it's more like 95%) and my takeaway is:

- it's fully possible

-- but the AI is of no great help with figuring out what the architecture or interfaces should be

- Keep a refactoring backlog

-- Spend 30%-40% of your time on refactoring, aligning patterns, improving architecture

-- depending on your codebase, this can happen in parallel

-- sometimes you need to get your hands dirty and do the cleanup yourself

-- ... but usually, you only need to establish the pattern once

- once the patterns are established, it becomes easy to talk to the AI in the context of your codebase

-- you can reference patterns by name or location

[fibonachos]

I should clarify. I do very little greenfield development, even outside of work. So my understanding of vibe coding being good for this use case is largely rooted in the relayed experience of others.