Amusing how this industry went from tweaking code for the best results, to tweaking code generators for the best results.

There doesn't seem to be any adults left in the room.

And seemingly we have stopped considering the fact that when we engineer something, we consider so much more than the behavior specified in the ticket.

Behavior built on top of years and years of experience.

And the problem with AI is that unless you explicitly 'prompt' for certain behavior you're only defining the end result. The inside becomes a black box.

Isn't having a prompt file turning the black box into an explicit codification of those years and years of experience? That would make it easier to understand and disseminate.

I haven't found their limit, but I have found my limits, of waiting for them to do their thing...

I tend to re-enjoy handrolling code more. I delegate the stuff that annoys me.

We have a large multiplatform codebase, the issue seems to be more the time it takes to navigate the code and reason about it, rather than the size. Arguably the size is causing 'them' to be slower in that regards, but I haven't found the limit yet. And with compaction, it's even less of a problem.

my 5c.

Exactly.

They wouldn't copy each other for copyright infringement as much as it was a mark of respect. They carried each other's arts as an evolution and respect towards each other rather than copying; all bringing a small twist on what was before.

This is the sort of Apple gotchas that really upset me.

They've got a good thing going, but they keep finding ways to alienate people.

Their suggestion : get an Apple monitor that we just launched.

I don't think that one supports this use.

Interesting I've never heard of waterfox before. Looks interesting!

I've covered it a few times on the Register. :-)

5Y ago:

https://www.theregister.com/2021/11/04/waterfox_firefox_fork...

Last year:

https://www.theregister.com/2025/12/18/firefox_no_ai_alterna...

This year:

https://www.theregister.com/2026/01/19/just_the_browser/

Any chance regular vim will some day get multiple cursors? That's the one thing I miss.

Agreed. I've been building software for 25 years+.

At some point I became so burnt out I couldn't look at an IDE or coloured text for that matter.

I found the way back by just changing my motto and focus... Find good people, do good work. That's it, that's all I want.

I don't care whether the 'property is hot' or what the market is doing anymore, I just build software in my lane, with good people around.

I noticed the training part, that was interesting for my use case. Unfortunately it's said 'on NVIDIA'.

Is there an alternative, tutorial, or project you'd recommend that would help me do supervised fine tuning (SFT) with the metal stack / macOS?

They state further down that they're working on non-Nvidia support. Looking forward to it, since I'm pretty heavily invested in suffering on AMD (ROCm sucks, but everything else about AMD is worth it to me.).

Use that mac to rent Nvidia gpus

> Mac: Like CPU - Chat only works for now. MLX training coming very soon

Time to jump ship.

I have noticed 5.3 in xtra high was a turd today. High used to be enough for most of my use cases. xhigh used to surprise me. Now it's incapable of following the very first instructions.

I just hope open source models get as good as last few month's top models before the enshittification has gone too far.

Kimi K2.5 has been great in my experience.

Exactly. Open models are a wrench in monetization plans. If a free model exists, and it’s ad free, then why pay for the proprietary model that comes with ads? It’s a worse product! Presumably you’d just use the better experience at that point

Qwen3.5 (-plus, which isn’t actually open to be fair) is surprisingly decent I’ve found.

Rule 5 is definitely king. Code acts on data, if the data is crap, you're already lost.

edit: s/data/data structure/

… if the data structures are crap.

Good software can handle crap data.

That is not what I meant. I meant crap data structures. Sorry it's late here.