1/ Controversial take: hard work is more important than smart work. It's a myth that we only have a few hours of good creative work per day. Train yourself to grind long hours first. You will surprise yourself. The work naturally become higher quality, less distracted.

To offend a strong man, tell him a lie. To offend a weak man, tell him the truth. —Marcus Aurelius

SOMEONE BUILT A SINGLE CLAUDE.MD FILE THAT FIXES EVERY BAD HABIT CLAUDE CODE HAS AND IT HIT 78.5K STARS it's based on andrej karpathy's public observations about how LLMs write code the problem he pointed out is that claude makes silent assumptions, overcomplicates everything,

Andrej Karpathy (Andrej Karpathy), OpenAI co-founder, ex-Tesla AI, "vibe coding" creator. In just 4 mins, he explains why Claude Skills, MCP servers, and AI agents are past the hype and are now the new baseline for building. Worth every second ↓

Karpathy didn't make a course. He made THE course. 3 hours. Free. Tokenization. Attention. Hallucinations. Tool use. RLHF. DeepSeek. AlphaGo. Every behavior you've ever wondered about in an LLM - where it comes from, why it exists, how it was engineered. The gap between

When you truly understand this 100% your key levels in the trending market become sharper and your win rate improves. P-Shape. b-Shape. Not just patterns they reveal who is in control of the market. 🔹 P-Shaped Profile Shorts are trapped. Price squeezes higher. Smart traders

Question/Answer time- Part 2-"How do option market makers source capital?" I think it's safe to say this varies tremendously across the industry- but for the most part these firms are private partnerships backed by owners equity (private capital)/ retained earnings and some

ANDREJ KARPATHY COULD HAVE CHARGED $500 FOR THIS WALKTHROUGH. He put it on YouTube. Every way he personally uses LLMs in his own life. Thinking models. Deep research. File uploads. Python interpreter. Claude Artifacts. Not theory. Not benchmarks. The actual daily workflow of

Most people look at AI and only see the first-order deflationary effect. But on U Got Options, I discuss with Lyn Alden why AI is an "incredible accelerant" for the populist cycle. The more it threatens white-collar wages, the more inflationary the fiscal response will

x.com/i/article/2048…

SOMEONE JUST DROPPED A NEW AGENT HARNESS THAT CLAIMS TO BLOW PAST CLAUDE CODE AND CODEX quick context: an agent harness is the layer between you and the AI and it handles prompts, tools, memory, and parallel sessions (e.g. codex cli & claude code) it's called jcode AND it's

Nobody talks about this enough... Karpathy’s Second Brain is great for Humans. But for Agents, markdown memory compounds Token Cost, Slower Retrieval, Stale Context, and Write Inefficiencies as Memory grows. This article breaks it down, and how Mercury solves it.

This closes a loop I've been working on for three months. Every agent harness debate has a hidden assumption: that the harness is a thing on top of the backend. Anthropic, OpenAI, LangChain, CrewAI argue about how thick that wrapper should be. Nobody questions that it's a

My current “take over the world” coding stack: ⁍ Hermes Agent ⁍ GBrain ⁍ GStack ⁍ Matt Pocock’s Skills repo ⁍ coffee ⁍ delusion ⁍ and terminals I’m afraid to close Agentic coding got weird fast. A year ago the stack was: ‣ React ‣ FastAPI ‣ Postgres ‣ Redis ‣ Docker

32K GitHub stars in just 10 hours! Warp is a banger terminal, one of the few tools I use that makes me believe good software still exists. so happy to see they joined open-source rather than fear security risks. and of course it’s rust.

Many agent stacks today are built around periodic snapshots of their knowledge sources. The wiki is re-indexed overnight, the codebase is re-embedded on a cron, the CRM is re-pulled on a schedule, and agents read those snapshots over and over, hoping to detect when something has

There's so much to explore in Hermes, check out the guide:

Introducing Kata Every trader has indicators in their head that don't exist on any platform. Kata changes that. Describe your setup → Kata writes it in kScript → it's on your chart. No code, no hassle. Just talk to it. One prompt. >Create a VWAP suite

daily reminder that cryexc alerts sends you a footprint screenshot every time a delta spike (absorption) or large trade happens ~3M in stops in hyperliquid right below this level btw link below

It was great to finally get Steve Hou on the podcast!