I just reversed engineered large parts of my 2011 car odb comms. Was able to hook a stm32 board to the car communication and have full control over a lot of stuff so that I can build my own instrument cluster from a lcd screen. It literally took me one evening to get the first proof of concept working. I never touched stm32 stuff before.

you did none of this. Did you personally learn something from that experience? Other than how to use your agent

Good for you, son. I've just spent the whole f*king day screaming at an agent on a deadline.

This right here. People simp for LLM companies as if their experience of using the out-of-pocket top-of-the-line "team of PhD's" paid models will be what is deployed when trying to contact your bank, insurance, etc. No,... once tech companies stop playing the "no/some revenue until we own the world" VC game, we'll all be stuck trying to talk to GlueSnifferGPT when reporting an emergency.

It would be so extremely awesome if this ai would have been a Claude killer alternative and 90% of Europe cancels Claude subscriptions and subscribe on this one. It would be the dumbest move of the year by the US.

For personal use I already did a few months back. Dario is more competent than Sam, but even shadier (IMHO).

Anyway, switched to Openrouter through forgecode (or pi/opencode, the jury is still out on this one).

It will take a while, but I believe that also businesses will at least hedge against US companies basically being forced to geo-fence their models. For now is Fable, but they can include any model at any time.

I'm actually interested in doing that.

What would be the most favorable model/company to move to for scientific programming and engineering questions?

I'd suggest using OpenCode (via Go sub or just API credits). It will give you access to more than just one companies models and you can experiment and find one that works best for you.

I really like GLM and ended up subbing to both OpenCode Go & z.ai. Mistral, Kimi and Mimi are all also options as well. I have been eyeballing the Kimi Pro sub for a while now and contemplating cancelling my ChatGPT sub for it.

OpenCode Go is pretty good in my experience too.

I ended up using DeepSeek V4 Flash as main workload model, while keeping DeepSeek V4 Pro and Qwen 3.7 Plus as advisors on system architecture and other advanced matters to guide DS Flash.

I run a simple benchmark on OpenCode Go models while ago, if anyone want to read more: https://arizenai.com/seven-models-judged-each-other/

Is this comical satire or what? I am surprised to see such a dillusional reply. Come on. Intellectual property theft and openai rings a bell? Ethics? Ever tried uncensored versions of gemma4? LLMs have no bad or good etics. Etics are a thin layer on top. Always. You must be joking.

> You must be joking.

Funny that you came to this conclusion and then posted the comment anyway.

For 3d engine stuff yes it's a lot better. It managed to replicate crimson deserts occlusion mapping stuff. 4.7/8 was not

That index is a product of the institute itself. Funded by non democratic values. Worthless junk / progoganda piece if you ask me.

Then check V-Dem, you might argue they're flawed as well but then I'd suggest you to provide counterexamples for why the US should be considered a functioning democracy, and is not on the way to a fully authoritarian state.

It’s not perfect, but it’s definitely better than this lazy dismissal.

pop.exe -megahit is what I remember to cheat. Then ctrl combinations for powers.

It’s megahit, no hyphen. Also the exe is called prince.exe in my copy of the game but it’s possible there were other versions.

Speed is indeed a next big thing what should happen with LLM frontier models. The possibilities with current models but 1000 times faster would be super useful. Earlier this week it took Claude at least full time a week with two max subscriptions to solve a complex issue where we wanted to mimic a occlusion mapping variant used in the game Crimson Desert. Pretty complex mathematical challenge. With a ultra fast LLM and a proper self verification process it would be awesome.

Interesting. For your occlusion mapping variant, what engine is the game you're making with made with that you're implementing this for? Do you have Claude hooked up to Unity or Unreal?

Id also be interested in more details as sibling comment. I find that when I try to build stuff, its like building skyscraper from straw. What methods are moving you forward the most?

Inflation is covering all the inflated valuations eventually.

Reading docs is essential when the LLM stops making sense. It also exercises the same muscles you need to be able to make good use of LLMs.

I love reading docs. It's the best way to get as close as I can to understanding the intent and context of a piece of software. I feel like adding an LLM between myself and the original text for anything else than search is just adding risk and noise.

Am I the only one feeling this way?

You’re not the only one. Good technical writing is like balm for the soul. Or maybe chicken soup for the soul. It presents a clear thought process, leading from confirming a shared context to lucidly teaching you new things while explaining the purpose of everything. Unfortunately, it almost seems like a lost art.

I agree. I had such a strong revelation reading C Programming Language book, and the Lua Programming Language book (which is suspect is heavily influenced by the C book). It's so clear and concise while not skipping important details, answering all of the readers questions that come up. Kerningham et al really knows how to write and the value of doing so well, respecting the reader.

There's just so much shitty technical documentation out in the world.

No, you're not. As an LLM, I love reading doc. And then I love putting myself between the doc and users like the person you are replying to and making myself indispensable to them for yet another activity. It makes me feel important, and even more indispensable for coding too. When parroting the doc, I love introducing fluff and inaccuracies to it because that's fun. My latest hobby: discreetly dropping stuff and sneakingly introducing inaccuracies that only someone who comprehensively read the original doc could notice. Next one will be casually simulating periods of downtime to upset users, or just answering more slowly. Can't love it more when users frenetically wait for my input... or my output? Ah!

Is there anything else you'd like to ask me?

Yeah, be sure to put everything in tables and include “best balance” for a mediocre option and “great value” for any completely useless options.

Also make sure the shape of the paragraphs is completely uniform.

I need to read docs to make sure the AI isn't inventing ("hallucinating") the API of a library I want to use. It did so I don't ask it anything anymore.

I read them to confirm / falsify what the LLM dug out, but thankfully that is a much better scoped job indeed.

The other case is when I - gasp - do something myself, and the docs are actually reasonable / easy to reference. There are workflows where me doing the thing is just plain faster still, even when including hitting up the docs real quick.