
Asahi kinda works, but only up to m2/m3. Apple isn’t very helpful with Linux support.

Asahi kinda works, but only up to m2/m3. Apple isn’t very helpful with Linux support.

Don’t step on snek

This Firmware was done with gemini (3.8 fast) so not even a very good model. I didn’t even look at the output as antigravity pushed the code directly to the keyboard and now it can do VIA. Usually I use fable 5.1 at work, which is obviously a frontier model. What I did do was set up the entire project by hand, added architecture files and do extremely detailed planning on what is to do. The I let the agent do the job, create tests and follow my initial design. Works pretty well. And even then, a reactor is cheap.

Sure thing, it just irks me that Lemmy overall is so negative. It’s basically the opposite of hacker news around here. Having looked at models and what they can do in recent months has been overall positive. Today I used it to write me a firmware for some Chinese hardware I had lying around that had little to no documentation and now does what I want it to do. There’s no harm in that.
Which models did you use so far?

Nah but that is a straw man argument you just brought up to argue against. That’s not very nice of you in a good faith argument.
I think the engineering part is misleading. If we’d built bridges like we build software. I’ve seen my fair share of legacy code in companies and it is far from what people think of it seems. Actually, that would be critique I have of LLMs. That they copy the style of a project, even if it is horrible.
That said, good models absolutely are helping with real world problems and Lemmy claims it’s literally the spawn of Satan. It’s a bit silly over a tool that has it’s uses. The effects on ram prices and datacenters in general leave plenty of room for us to bicker over, but it’s undeniably a good tool for both debugging and some coding.

Software engineering has always been bad. People just copy pasted stack overflow. Now an LLM copies stack overflow and the documentation.
Someone put in the intro to the book Frankenstein into an ai checker and it confirmed it to be 100 percent written by an LLM. It’s not deterministic.