I think there has to be a better rubric by which person would be evaluated, not just amount of tokens they managed to waste.

Very true, but this also makes me think what kind of ridiculous obstacle course future hiring process would look like.

In a land where anyone with a pulse can prompt AI to make an app for them - how would future hiring managers and team leads figure out who will drag codebase down with tech debt and who wouldn't?

I very regularly use plan mode not to even make a plan of action itself, but to better understand what possible issues might come up when implementing some feature or fixing some bug. And it is quite common for me to fix or rewrite certain findings that AI comes up because its assumptions are not quite right or don't align with overall goal.

And yet so many seem to be perfectly fine leaving all the decisions to AI - even if it's going in the wrong direction. I suppose that's all the people who got into software purely for money or status - never really caring about the actual thing they are working on.

Is this what happens when you vibe code long enough?

The movement does look pretty neat. I'm not into watches, but it's impressive that purely rendered thing was designed to be realistic.

Furthermore, there are some clearly wrong questions where person asks AI to make some kind of numerical evaluation of some data. And evaluation is done entirely through inference - essentially a hallucination, instead of some one-off python script which can actually give deterministic calculated evaluation. Yet they accept the answer AI gives them.

Same thing with hobby projects - I might ask ChatGPT or Gemini some questions about best practices in Swift for example, but writing code is done by hand.

As others said - if you don't use it, you'll lose it. And I'd rather keep my skills up to date.

I can't tell how much less resources it uses - haven't really tested that. To be fair to VSCode often times biggest resource hog is various language servers.

Not sure if it's the lack of color in general or because screens kind of turn into a black and white mush that's hard to navigate.

I've met in my professional life some managers or other middlemen who would be profoundly incapable of producing correct software no matter how smart of an AI agent they have access to. One of those - you don't know what you don't know.

But, I guess this is the world we live in now. Going to be Mortal Kombat for positions in companies where software engineers are actually valued.

There are some precedents and rulings related to copyright and AI, so we have at least some rubric by which "authorship" can be determined. But when it comes to AI doing polishing of existing code - that is less certain.

It is a fairly painful process - I am using Codex and Claude as a first pass for converting things, but everything has to be checked manually and often fixed or rolled back to try again. Too often instead of "removing" piece of code that is not necessary anymore, AI would try to add a 100 line workaround for it because it would really rather add things than remove them.

It is, however still a faster process than doing manual rewrite. Smaller components are a breeze to convert from older Vue 2 to Vue 3 composition API.

Rewriting entry point app.ts with bunch of custom plugins was a horrendous experience that eventually was done manually. Move from Vuex to Pinia was also 50/50. Some things were easy, some things were not and had to be done manually.

Then there's a process of switching from unsupported packages which is a whole other can of worms.

Overall - if not for AI I'm not sure I'd have gone with an upgrade at this point. Yes it requires careful review and testing, but a ton of trivial stuff was done very quickly.

Plus some additional features like payments through QR.

I wonder if healthy diet also plays role in the outcome.