Good? My Macbook m3 with 36gb locked up after it filled all memory with Gemma4. A bit useful yes. But it eats all resources. For local models to be useful we need at least 128gb of system memory and 512gb of video memory. Plus 8 times the compute of a single 5090/h200
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.
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.
Of course I learned from it. I mean the reverse engineering part which is basically try and error is something I rather skip. The remaining things like wiring the hardware is still there. The boring stuff is what the LLM can do for me. I still find the process to get stuff working challenging and interesting. It's not only about the end result. It's just a different approach than the old school low level one
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'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.
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.
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.
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.
You are misinformed. Ukraine is used as cannon fodder by western institutions. You talk about Ukraine taking decisions. I can tell you that the normal Joe in Ukraine is completely sidelined in decisions. The whole country is controlled by foreign powers. A lot of western people call this Russian propoganda. They can't see that their own governments are at the wrong side of history. In the meantime it's hypocritical behavior is visible all over the world.
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?
reply