Terrasque

When you run it, do you use unsloth’s recommended settings for coding?

https://unsloth.ai/docs/models/qwen3.6

Also have preserve thinking on, it helps it stay consistent in multi turn work.

Which model version you’re using can also affect results, usually unsloth’s ones are good.

With all that said, it’s of course a small model so it’s not a super coder. The 27b is better (I’d guess 25-35% better), but of course still a small model so…

So it’ll maybe not be good enough still, but should give it the chance to let it do the best it can :)

Try qwen3.6-35b-a3b with a lightweight harness like pi.dev

Having it be able to run commands and try to compile or run the code and see the output helps especially on the “doesn’t compile” part of things

Next logical step would be to sue producers of radios, speakers, headphones and so on, I assume. Their devices “perform” the music, after all.

And then they can sue hospitals for helping bringing new ears into the world.

I found out the hard way this is not entirely correct, as a user found a valid json that yaml parsers didn’t handle. IIRC it was some exotic whitespace issue

I’d think the main users of GeForce now are people who don’t play games that much and won’t spend that much money on gaming hardware.

Let’s be generous and say $100. That’s 6 months with the most expensive tier.

That should be plenty to get a gaming PC capable of playing latest AAA titles in 4k 60 fps and high settings.

It’s one computer, Michael. What could it cost, 10 dollars?

I paid $200 for ultimate for a year and got borderlands 4 included in it.

You’d be challenged to build a decent gaming PC for 3 times that.

Republicans

You’re pushing code to prod without pr’s and code reviews? What kind of jank-ass cowboy shop are you running?

It doesn’t matter if an llm or a human wrote it, it needs peer review, unit tests and go through QA before it gets anywhere near production.

If you got good internet you could look into GeForce Now as a stopgap / headstart.

It’s using an x86 compatibility layer, pex i think it was called. So apparently you will be running windows x86 games on it.

Edit: fex! https://github.com/FEX-Emu/FEX

Edit 2, from tom’s hardware article:

The company also showed off the x86 version of Hades 2 running standalone (as in not streaming from a PC) on the Steam Frame. And the game ran just fine and looked good at what Valve reps told me was 1400p in a window inside the headset

Enlightened dumbness 🧘

It regurgitates old code, it cannot come up with new stuff.

The trick is, most of what you write is basically old code in new wrapping. In most projects, I’d say the new and novel part is maybe 10% of the code. The rest is things like setting up db models, connecting them to base logic, set up views, api endpoints, decoding the message on the ui part, displaying it to user, handling input back, threading things so UI doesn’t hang, error handling, input data verification, basic unit tests, set up settings, support reading them from a file or env vars, making UI look not horrible, add translatable text, and so on and on and on. All that has been written in some variation a million times before. All can be written (and verified) by a half-asleep competent coder.

The actual new interesting part is gonna be a small small percentage of the total code.

I guess I’m one of the idiots then, but what do I know. I’ve only been coding since the 90s

That’s kinda wrong though. I’ve seen llm’s write pretty good code, in some cases even doing something clever I hadn’t thought of.

You should treat it as any junior though, and read the code changes and give feedback if needed.

I’ve used Claude code to fix some bugs and add some new features to some of my old, small programs and websites. Not things I can’t do myself, but things I can’t be arsed to sit down and actually do.

It’s actually gone really well, with clean and solid code. easily readable, correct, with error handling and even comments explaining things. It even took a gui stream processing program I had and wrote a server / webapp with the same functionality, and was able to extend it with a few new features I’ve been thinking to add.

These are not complex things, but a few of them were 20+ files big, and it manage to not only navigate the code, but understand it well enough to add features with the changes touching multiple files (model, logic, view layer for example, or refactor a too big class and update all references to use the new classes).

So it’s absolutely useful and capable of writing good code.

“Better shoot some blacks to avenge it”

I’ve found it useful to write test units once you’we written one or two, write specific functions and small scripts. For example some time ago I needed a script that found a machine’s public ip, then post that to an mqtt topic along with timestamp, with config abstracted out in a file.

Now there’s nothing difficult with this, but just looking up what libraries to use and their syntax takes some time, along with actually writing the code. Also, since it’s so straight forward, it’s pretty boring. ChatGPT wrote it in under two minutes, working perfectly on first try.

It’s also been helpful with bash scripts, powershell scripts and ansible playbooks. Things I don’t really remember the syntax on between use, and which are a bit arcane / exotic. It’s just a nice helper to have for the boring and simple things that still need to be done.

Just can’t waste time on trying to make it do anything complicated because that never goes well.

Yeah, that’s a waste of time. However, it can knock out simple code you can easily write yourself, but is boring to write and take time out of working on the real problems.

When you cosplay as judge dredd, it’s exactly how it works