The WTI oil price is still following the roadmap for higher prices. This is not yet a decisive upside breakout, however. A test of the support zone is possible before the next leg up starts.

Insightful

Over the next 30 days many will create generational wealth from the S&P 500… Currently the McClellan Oscillator & RSI readings on $SPY are the most oversold since April 2025. The last time, I spotted this setup $SPY blew to a new ATH before collapsing. This exact playbook

An agent can modify dozens of files, call APIs, run commands, and change a codebase — yet when something fails, we’re stuck scrolling through terminal logs. That’s the Agentic Observability Gap. If agents are going to run autonomously, they need: 🔍 traces 🚨 alerts Medium

Whichever way the GSR breaks by the end of the week is the way I see the trend going for the next couple of weeks. A break through support leads me to expect levels around 35.

$BTC 2026 Bull Run Outlook Feb → Bear trap Mar → Breakout Apr → Altseason May → New ATH near $215K Jun → Bull trap Jul → Liquidation cascade Aug → Bear market begins I’ve called major market tops and bottoms for over a decade. I warned about the October top — and I’ll do

x.com/i/article/2034…

Honestly, the relentless upward price action was more challenging emotionally than the correction has been. No one likes round-tripping — but when the price is running away FOMO is harder to zen than the excitement of buying the discount. Good news! The intrinsic value of

👀

👀

$SPX Eerily similar innit?!

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating

Building a personal knowledge base for my agents is increasingly where I spend my time these days. Like Andrej Karpathy, I also use Obsidian for my MD vaults. What's different in my approach is that I curate research papers on a daily basis and have actually tuned a Skill for

Orchestrates multi-agent pipelines for development automation github.com/stephenleo/bma…

How to Train Your Advisor: Steering Black-Box LLMs with ADVISOR MODELS Medium Anthropic link: medium.com/ai-artistry/ho…

OpenClaw meets RL! OpenClaw Agents adapt through memory files and skills, but the base model weights never actually change. OpenClaw-RL solves this! It wraps a self-hosted model as an OpenAI-compatible API, intercepts live conversations from OpenClaw, and trains the policy in

Would be interesting

🚀Introducing Motus, the open-source agent infrastructure that learns in production. Existing agent infra serves static agents: the harness, model, and workflow are fixed after deployment. But static agents degrade over time. The harness goes stale, new models go unincorporated,

insightful