Working with AI

The craft of talking to a model that will take you exactly as literally as it decides to

Forcing the model to fill in a shape — and why it's harder than it looks.

The JSON-shaped API that turned chat models into clients of the real world.

Why AI models confidently make things up — and what you can actually do about it

How AI learned to look things up before opening its mouth

Why the document your RAG system retrieves first is rarely the document you want.

When AI stops answering and starts doing — and then, very often, hits a wall

How AI agents remember things across runs — and why most of them don't, really.

What happens when AI models try to coordinate with each other — and the new failure modes that come with it

The open standard that lets AI models talk to your tools without a custom integration per model

How you measure whether a model is good at the thing you actually care about.

The new SQL injection — when input data quietly becomes instructions the model follows.

How users get aligned models to do what they were trained not to do.

The problem of building AI that reliably does what you actually wanted — not what you literally asked for

When the model judges itself — Anthropic's bet on alignment without exhausting the rater pool.

Invisible signatures on AI-generated text — and why most don't survive contact with reality.

The documentation labs publish when they release a model — and what they leave out.