I don't know,.any developer who would not deliberately decide to not use ai would be easily becoming better in using ai as any non technical person.

Non technical people are usually not even able to use versioning software in a good way.

A developer could hold the ai on the rails. And understood when things go in the wrong direction.

So yes pure vibe coding might be a thing. But I don't think vibe coders would outperform developers if the dev would also use an ai in any form. Of course maybe they are cheaper. But no real competitors on the same level.

I think it could also be a good time for middle size open source projects.

I built a middle size one which I didn't have started before the era of ai, because i didn't have enough time for it.

But with the help i could concentrate more on design decisions and trade offs. Also i learned a lot of the ai generated code because it was on a domain which was quite new to me.

So i guess not all open source ai contributions are slop. And maybe we will see a rise of middle size projects done by devs who hadn't had enough time for it beforehand.

Hey i build a K2 compiler mutation lib for kotlin.

The cool thing is that you only have to compile once. Then all mutation points are configured and enabled in a row via junit extension. So it just works within your test suite.

The title is click bait.

Nothing complex could be built without some form of abstractions.

That abstractions are not always right and they could leak is a correct observation. But far away from anything new.

The article is correct but trivial, the title is purely click bait.

Hey, this was quite a long read. But the outcome seemed.to me as a.software engineer quite obvious.

I would never use any Workflow where there is no readable source code artifact as an outcome.

Sure first of all for Humans to understand and to avoid cognitive debts.

But also for the AI for later sessions and adjustments. Also an ai needs good readable code to understand the code in the long run.

I agree but I guess another point I didn't make clear was that the feedback is not the same as the code. We can not assume that all the feedback can be embodied in the code and even if we could my ultimate point was that we need system that can learn on the fly and current systems don't.

Take an intern for example, they learn only fly and they do this in a compounded fashion where previous learnings inform new ones. Current systems can't do this, the only way to do this effectively is to change their weights in real time but we don't know how to do that yet

Yes i guess with the current ai we don't have this kind of learning. What works best for me.is to store important learnings in a instructions file or skill. Also i generate these days always some extra documentation about the overall design.

This helps to get the ai on the loop for the nest iteration or feature m

But yes this is limited and also takes some of the rare resources of context window.

But as you said we cannot do this kind of learning with weight's with our current llms.

I guess it's all useful but it's also quite different from human thinking. And i guess we have to guide here to get the best out of it.

100%.

I will update the post to better illustrate my point and tie the intervention point and the continual learning point together. Thanks for the feedback

edited: I have updated the post