Lunar (@LunarResearcher)

Most people are trying to improve AI agents at the wrong layer....

Anthropic just dropped a free 59-minute Claude Code course From autocomplete to real AI agents: 0% → 00:00 - move from autocomplete to agents 20% → 04:50 - understand how the agentic loop works 40% → 14:07 - use CLAUDE.md as project memory 60% → 26:53 - learn why Plan Mode comes first 80% → 33:31 ...

Most people building multi-agent AI systems are focusing on the wrong layer....

## A Practical Guide To The 3 Layers People Keep Mixing Together...

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treat...

Google just released a free 1-hour course on full agentic systems. How to go from one agent to 1,000 agents running while you sleep: 07:02 - Build your first agent 13:34 - Give each agent a real skill 23:08 - Engineer the context they need 32:56 - Turn agents into graphs 54:11 - Run 1,000 agents i...