vivendi

if nothing else it should be easier with rust because:

a) That fucking syntax is probably more legible to an AI than a human (sue me, Rust absolutists)

b) The language has more safety barriers; making use of AI safer by association

This is luddite behavior. AI can be a very valuable tool for learning unless you're working with some truly exotic shit (in which case pray to RAG to save you)

YO; extremely rare D mention

I discovered digitalmars back in the very early days; it's been on my watchlist for over 15+ years now

I've done more off-roading in my IKCO sedan (Iranian car manufacturer)

between lapse and zed I also decided on Lapse because it feels much more community-oriented than Zed; maybe you should look into that

Technically this shit isn't even free (libre); atleast with corpo projects we can always fork them

I wish there was a GCC equivalent; but even if clang is a corpowhore project it's atleast OSS

Well; companies used to get anti-trust laser canon'ed from orbit for less; but good luck with that in modern America

I know people like to hate on google, but google is actually like 3 companies in a trench coat.

They do highly valuable open source / open ecosystem work (I will say the chance of you indirectly using a google tool without knowing is over 90% now) and if the American government, a capitalist fascist government no less, gets their hands on it, we're fucked

Not all of google is adsense or YouTube.

Another great thing about BTRFS is that it can detect hardware problems sooner: if your BTRFS drive keeps losing data to corruption; that's because it has detected a corruption that other FS's would silently work with

BTRFS FUCKS; HARD

Inference costs are very, very low. You can run Mistral Small 24B finetunes that are better than GPT-4o and actually quite usable on your own local machine.

As for training costs, Meta's LLAMA team displace their emissions with environmental programs, which is more green than 99.9% of any company making any product you use

TLDR; don't use ClosedAI use Mistral or other foss projects

EDIT: I recommend cognitivecomputations Dolphin 3.0 Mistral Small R1 fine tune in particular. I've only used it for mathematical workloads in truth, but it has been exceedingly good at my tasks thus far. The training set and the model are both FOSS and uncensored. You'll need a custom system prompt to activate the Chain of Thought reasoning, and you'll need a comparatively low temperature to keep the model from creating logic loops for itself (0.1 - 0.4 range should be OK)