IMO those are 2 small categories, at the very extremes of the curve. It’s also way more complicated than that. I enjoy coding and delving into hard problems. I also enjoy quickly turning ideas into results. I also sometimes find coding a chore. AI is a tool, use it where it makes sense.

No I don’t believe that. AI on the whole enhances people’s ability to express their intent. Whether they write by copying code from samples, or getting AI to write it (and hopefully learn from it), it doesn’t really matter imo.

I do agree, but there’s I also want to challenge the point that only human’s can create ‘quality’ code. I’ve seen a *lot* of times where the code produced by someone using AI is better than what they would have produced without AI.

Sure, but the opposite can also be true. You spend too long contemplating that you don’t get anything in front of users for feedback, etc.

It’s not really meant to imply anything. AI is a tool, and it’s up to you how you use it. Sloppy code and shipping unfinished features isn’t just a problem with AI, human devs have been doing that for a whole lot longer.

I think that’s a bit too reductive. Treating the fact that a system can do X as evidence of the system’s purpose stretches the premise well beyond usefulness.

Ignoring a (very good) tool because you can write lots of sloppy features feels a bit like ‘cutting your nose to spite your face’. As a counterpoint, nearly all of Haze’s Glass impl was written by GPT. I orchestrated the approach, code, tuning & testing, and I am personally happy with the result.

Here's a little preview of the new glass effect coming to Haze 2.0 Should be in the next alpha release

Hunting down Jetpack Compose recomposition issues manually is a huge time sink I’ve spent the past few weeks using @mmckenna.me’s Dejavu to simplify this: - Write Dejavu tests to establish a baseline - Tell the agent to hunt for issues and A/B fixes - Profit

Thanks! Ideally, distribute your own.