The market has doubted @elonmusk before... Didn't last long. $TSLA $SPCX

Elon: I've got a fucking IPO tomorrow bro. Cut this war shit out. We've got midterms in a few months Trump: alright bet

BREAKING: Bitcoin drops below $60,000 for the first time since October 2024. It's now down 27% in the last 20 days, wiping out $460 billion in market cap.

How it feels holding overnight after seeing this:

🇺🇸 Trump just walked through his cognitive test, step by step. Only Trump can turn a medical exam into a victory lap in front of a live audience. "Pick a number, sir. Okay. 203. Multiply times 9. Divide by 2. Add on 1,324. Subtract 1,292. Sir, multiply it out one more time by 19. What is the answer, sir?" "And I got it right!" "And the one doctor said, I've been doing this test for 20 years. I've never seen anybody ace it." "So I've taken it and I've aced it all three times, I'll tell you. Because it is a positive thing. Nice to be smart!" The man aced it three times and he will tell you about it until he aces a fourth. Source: @EricLDaugh

Today in 1940, the Nazi blitzkrieg of France began when German forces crossed the Muese River. Blitzkrieg tactics 👇🏼

🚨 ULTIMA HORA : Alguien acaba de matar la suscripción de Claude Code. Se llama free-claude-code. Un proxy open-source que convierte las llamadas a la API de Anthropic al formato NVIDIA NIM, y te da 40 requests por minuto completamente gratis. La config tarda 2 minutos: consigues una API key gratuita de NVIDIA, apuntas Claude Code a localhost, y listo. Sin factura. Sin panic de rate limits. Sin depender de un solo proveedor. Soporta Kimi K2, GLM 4.7, MiniMax M2, Devstral y más. Streamea thinking tokens y tool calls en tiempo real. Y tiene un bot de Telegram integrado para que controles Claude Code desde el móvil. Esto no es un OpenRouter más. Convierte Claude Code en un agente libre que tú controlas desde cualquier sitio. Código en GitHub. Se llama free-claude-code.

3 months ago, I realized I was hopelessly dependent on corporations that only care about power, money, and control. At this point Cursor, Claude, OpenAI, all had rugged their unlimited plans. I wanted a Mac M3 Ultra with 512GB RAM. Ahmad and Pewdiepie convinced me otherwise. Here's what I learned building my own AI Rig ----------------------------- The Build ($3K-$10K) This is the top performance you can get below 10k USD • 4x RTX 3090s with 2x NVLink • Epyc CPU with 128 PCIe lanes • 256-512GB DDR4 RAM • Romed8-2T motherboard • Custom rack fan cooling • AX1600i PSU quality risers Cost: $5K in US, $8K in EU (thanks VAT) Performance Reality Check More 3090s = larger models, but diminishing returns kick in fast. Next step: 8-12 GPUs for AWQ 4-bit or BF16 Mix GLM 4.5-4.6 But at this point, you've hit consumer hardware limits. ---------------------------------------- Models that work: S-Tier Models (The Golden Standard) • GLM-4.5-Air: Matches Sonnet 4.0, codes flawlessly got this up to a steady 50 tps and 4k/s prefill with vLLM • Hermes-70B: Tells you anything without jailbreaking A-Tier Workhorses • Qwen line • Mistral line • GPT-OSS B-Tier Options • Gemma line • Llama line ------------------------------------ The Software Stack That Actually Works For coding/agents: • Claude Code Router (GLM-4.5-Air runs perfectly) • Roocode Orchestrator: Define modes (coding, security, reviewer, researcher) The orchestrator manages scope, spins up local LLMs with fragmented context, then synthesizes results. You can use GPT-5 or Opus/GLM-4.6 as orchestrator, and local models as everything else! Scaffolding Options (Ranked) 1. vLLM: Peak performance usability, blazing fast if model fits 2. exllamav3: Much faster, all quant sizes, but poor scaffolding 3. llama.cpp: Easy start, good initial speeds, degrades over context UI Recommendations • lmstudio: Locked to llama.cpp but great UX • 3 Sparks: Apple app for local LLMs • JanAI: Fine but feature-limited ------------------------------- Bottom Line Mac Ultra M3 gets you 60-80% performance with MLX access. But if you want the absolute best you need Nvidia. This journey taught me: real independence comes from understanding and building your own tools. If you're interested in benchmarks I've posted a lot on my profile