(re)reading @Juraj 's Tamers of Entropy and a line hit very deep "wait 10 years and they will be arguing about code of conduct instead of code" , describes the hacking community so well, I stuck around until late 2010s but by then it was already completely overtaken by everything else than the actual hacker spirit

GFM!

i've done some crazy things in my life but nothing this insane

Vibe struggle

hoard them gpus ppl

Crypto Briefing

RENDER Network faces negative GPU supply for first time since 2018

Render Network recorded negative GPU supply for the first time since 2018, as AI workloads surge to 35-40% of activity and token burns jump 279%

good perspective on what the "justice system" is using to lock you up

god forbid people have control over anything, that needs to be completely eliminated as soon as possible. Its only his controlled propaganda that should be allowed to be used, and obviously you need to be kyc'd for it so you can properly get the correct amount of reprogramming thats needed for the powers at be to keep you docile. View quoted note →

Its baffling how @primal can still have broken text editor on android after all this time

new day new experiment (yes, there was a hackathon) local inference on mobile with qvac sdk and @ContextVM support for tool use and discovery

GitHub

GitHub - aljazceru/kvaq

Contribute to aljazceru/kvaq development by creating an account on GitHub.

i'll never understand people who prefer phones over computers. You weirdos.

I'm at the "i can't figure out where my agent that i'm talking to is actually running" stage of AI psychosis

i'm contemplating to get macbook neo as a occasional build machine for ios/apple ecosystem? or would it make more sense to buy an old mac mini? How old can it be to still have supported things needed to build apps? (as you can see i'm extremely familiar with apple ecosystem)

confidential inference without verifiability is just trust-me-bro with extra steps I've added attestation checks so now you can see which providers actually let you verify their TEE claims vs which ones make it nearly impossible. The goal is to bring more transparency and accountability to inference providers. turns out there's a lot of theater in this space.

Confidential Inference

Attestation Monitor — Confidential Inference

Zero-trust TEE attestation verification for confidential inference providers. Cryptographic verification of Intel TDX, AMD SEV-SNP, and NVIDIA GPU ...

"make it less romantic, i want the cpu smoking after sex" - too kinky for openai apparently

i'm definitely rethinking running all the public nostr infra because some of the takes around here are so retarded i'm afraid my hardware might kill itself after seeing them