Deep Dives
Go Deeper. Build Smarter.
Long-form technical deep dives, hands-on labs, and builder workbooks. The stuff that doesn't fit in a weekly briefing.
Deep Dive · Standalone Feature Mar 2026
NVIDIA Just Put a Cage Around the Lobster
NVIDIA launched NemoClaw at GTC 2026 — an open-source security and deployment stack for OpenClaw agents. Here's what it actually does, why it matters, and what builders should do about it right now.
→ Lab 3 · Advanced Mar 2026
Lab: Ship Your First Secure AI Agent with NemoClaw
Hands-on lab: deploy a sandboxed OpenClaw agent with NemoClaw on WSL2, macOS, or Linux. Includes the workaround for the GPU sandbox bug and the first confirmed GPU passthrough on WSL2.
→ Deep Dive · Standalone Feature Mar 2026
I Let an AI Do ML Research While I Slept
We gave an AI agent a laptop GPU, a training script, and a set of research instructions written in English. Then we went to sleep. It ran 127 experiments overnight, and its biggest breakthrough broke every rule in the ML textbook.
→ Deep Dive · Standalone Feature Feb 2026
The Agent Identity Crisis
Your AI agents don't have IDs. In 6 months, that's illegal. The compliance cliff, the protocol identity gap, and the biggest builder opportunity in the agentic stack.
→ Deep Dive · Companion to Issue #001 Feb 2026
The Protocol War That Isn't: MCP vs A2A
The two protocols that will run every AI agent by 2027. Full breakdown, comparison table, honest cons, hype scorecard, and a 3-lab hands-on workbook with runnable code.
→ Lab 3 · Advanced Feb 2026
Dual-Agent Architecture: Structured Work Channels
The lab that separates builders from bloggers. Structured JSON between agents, natural language only for humans. 83% token savings. Full code included.
→