ree2raz

geek . complexity skeptic . rejecting slop

[ree2raz @ree2raz]

@dillon_mulroy earlier it was ignorance now mf-ia are rage baiting.

[ree2raz @ree2raz]

@lVlarty @HealthcareAIGuy ha^3

[ree2raz @ree2raz]

@reach_vb hoping for another win at home for sir lewis.

[ree2raz @ree2raz]

@vivekgalatage UNIX philosophy >> philosophy

[ree2raz @ree2raz]

@nntaleb hence, to balance your heightened creativity,
1. expand your body of knowledge
2. increase your capacity to remember

[Take Testosterone @maxyourtest]

4am mindset

[ree2raz @ree2raz]

@yash1_ @yashetal elon is ahs

[ree2raz @ree2raz]

@yash1_ @yashetal done

[ree2raz @ree2raz]

@__tinygrad__ @icanvardar word

[ree2raz @ree2raz]

@sudoingX @AMD You can checkout that PR: 21344 and follow the steps to build and flags to set. I don't have strix halo but after your bench run I was reading about the prefill speed difference between AMD and NVIDIA. Then I found out about this PR that was closed but had gfx1151 optimization.

[ree2raz @ree2raz]

@ranaharshraj7 @huggingface I love @huggingface but ml-intern can be replaced with an hugging-face agent-skills suite.
I tried it and it feels unnecessary.

[ree2raz @ree2raz]

@__tinygrad__ congratulations, "commoditize the petaflops" 🚀

[ree2raz @ree2raz]

@DavidOndrej1 The current physical world is built on chinese steel,
future AI world will be built upon chinese models
that's what is a win for china

[Sudo su @sudoingX]

people keep asking me, if you were starting over today with nothing, how would you do it.

here is the honest answer, the one nobody wants because it isn't sexy.

i would buy the cheapest used card that runs a real model. a 3060 12gb, 200 bucks, and i would not spend another cent until i had squeezed everything out of it. not because i couldn't dream bigger, but because the card was never the thing standing between me and the work. it never is.

everyone thinks they are one purchase away from being ready. one more gpu, one more course, one more follower count, one more month of learning quietly until they feel good enough to be seen. and they stay there for years. waiting to be ready is the most expensive thing you will ever buy, it just never shows up on a receipt.

i started scrappy and i stayed scrappy on purpose. i posted the small wins, the cheap setups, the ugly first benchmarks, the stuff that felt too small to matter.

and the small stuff is exactly what people needed, because most of them are sitting where i was sitting, staring at a spec sheet they can't afford, convinced they can't begin.

you can begin. today. with whatever you have.

[ree2raz @ree2raz]

@sudoingX if you start today, what gpu would you start with ?

[ree2raz @ree2raz]

fuse you LLMs output via @OpenRouter and find out the combo that works best for you.

[OpenRouter @OpenRouter]

Introducing the Fusion API, the smartest compound model in the market.

Fusion achieves Fable-level intelligence at half the price.

How it works 👇

[ree2raz @ree2raz]

@charles_irl that's why you need to keep GPU busy
it wanders into kafka land when idle

[ree2raz @ree2raz]

@sudoingX is the real deal if you are interested in Local AI.

[Sudo su @sudoingX]

https://t.co/YluHf74Xo9

[ree2raz @ree2raz]

@ranaharshraj7 keep sharing good stuff, x payout is loading...