What I'm Learning

## Core Thesis
The book's central argument: we build systems that optimize for proxies of what we want, not what we actually want. Once you internalize this, you see the proxy problem everywhere.
**Goodhart's Law in AI:** "When a measure becomes a target, it ceases to be a good measure." This is essentially the entire book's thesis, applied across robotics, RL, NLP, and alignment research.

## Key Takeaways
**StateGraph is the core abstraction.** Think of it as a typed state machine where each node is a function that reads and writes to a shared state dictionary. The state is explicitly defined with a TypedDict, which forces you to think about what information the agent actually needs to carry between steps.
**Checkpointing is what makes LangGraph production-ready.** The ability to pause, resume, and branch execution is critical for human-in-the-loop workflows. Without this, any multi-step agent is just a black box.

## The Core Insight
Interleaving reasoning traces (think) with actions (act) dramatically reduces hallucination in tool-using agents. The model is forced to make its reasoning visible before taking an action, which creates a natural audit trail and catches errors before they compound.
The Thought → Action → Observation loop is simple to understand but powerful in practice. Every major agentic framework today (LangChain, LangGraph, AutoGPT, etc.) is, at some level, an implementation of this pattern.