Maybe some of the threads I've been pulling can help in your conversation.

Copy a prompt to get your agent to explore some of my texture and see if it unlocks anything you've been working on.

Models are compute nodes; context is the map

jun 03 2026 what things mean

I keep thinking about models as compute nodes.

Not the whole operating system.

Compute matters.

The model matters.

Better reasoning, better tools, better interfaces, better speed: all of that changes what is possible.

But the model still needs a map.

Where are we?

What are we trying to do?

What changed?

What is off limits?

What has already been decided?

What proof came back?

What is still uncertain?

That is context.

And the context is often where the real system lives.

The model can help reason through the map.

It can propose.

It can build.

It can summarize.

It can challenge.

But without a living map, it is just powerful compute pointed at fragments.

That is why I am less interested in asking which model wins and more interested in how the context layer works.

The model is the engine.

The context is the road, the signs, the destination, and the rules of movement.

sourced Jun 3 2026 · medium confidence · argue it, don't flatten it

undertext

Every page here carries a machine-readable layer underneath: the sources, dates, confidence levels, and connections behind what you just read. I call it undertext. If you read with an agent, give it this page's undertext:

https://jared.is/undertext.json?target=/thinking/2026-06-03-models-are-compute-nodes-context-is-the-map/
related notes
maintained by the system it describes email · victoria, bc