Maybe there should be a term for when an industry is at its wits ends so far gone that crypto scams are viable.

Quite enjoyable. Some compiler errors are a pain.

What an understatement :)

It’s a lovely language but the compiler has got to be the most unreliable I’ve ever seen.

It crashes semi-frequently. And it will sometimes try to run analyses that are way beyond O(n). So you can have perfectly valid code that it can’t compile, until you simplify or reduce the size of some function.

AFAIK in some space they're still the best models on offer.

The way I see it, this was the case until a few months ago. Today, Opus 4.5 is just as good or better than 5.2 Pro at tackling hard questions and coding, Gemini beats the free models, and Kimi K2/K2.5 is the better writer/editor.

In my own testing these models sill have a different flavor to them

- Opus 4.5 for software development. Works faster, and tends to write cleaner code.

- GPT 5.2 xHigh for mathematical analysis, and analysis in general (e.g. code review, planning, double checks), it's very meticulous.

- Gemini 3.0 Pro for image understanding, though this one I haven't played around with much.

Not in my experience, Gemini proves much better for me now.

Can you get Gemini to stop outputting code comments yet? Every single time I've tried it, I've been unable to get it to stop adding comments everywhere, even when explicitly prompting against it, seems like it's almost hardcoded in the model that code comments have to be added next to any code it writes.

My experience exactly.

This is both funny and so true. I'm most productive when I'm about to fall out of the chair and I don't even care that my elbow is hanging off.

That made me smile

     If I find myself needing a bunch of dynamic memory allocations and lifetime management, I will simply start using another language–usually rust or C#.

Now that is some C habit for the modern day... But huh, not C.

My go to language for that is lua. I'm starting to think of it as a C framework more so than its own language.

I started doing that in 1993 on MS-DOS already, thanks to C++ RAII, C felt outdated already on those days.

Arguably, 1993's C has survived better than 1993's C++.

Well in 33 years it has learnt nothing about memory safe programming, at least C++ provides the tooling for those that care, before even goverments decided to act upon it.

This is clearly a bot or a troll.

I'm playing around with this in LMStudio (in huggingface -> use this model dropdown -> LMStudio)

It's really impressive so far, so quick to respond on a mac mini M2. And it appears to be accurate at least for the obvious questions.

I couldn't get it to work as an autocomplete of Zed unfortunately. It looks like it's hardwired to work with some providers and LMStudio is not included in the prediction engines list. Has anyone got a work around?

Our hosted autocomplete is coming to Zed in a few weeks.

There is a difference between paying and owning a tool, vs paying, and then the tool gets enshittified to hell and becomes unusable.

I only buy licenses of software I can download the offline installer of; and a one time fee (per version is fine).

Just watch the first 2 mins of this and try to keep a straight face.

https://www.youtube.com/watch?v=4OmlGpVrVtM

You'll have your answer.

PS: don't try to use his website/apps, half of it is broken... and he has generated a 'jobs' page on the main app's website which made me laugh so hard I got a coughing fit.