Root & Reason

All articles

Browse by tag →

Models & Monsters

The Goblin who filed feature requests: How unexpected AI behaviour shaped my multi-agent harness.

local-llmdotnetmeasurementagents

Can a small model be a good agent?

Twenty-eight models, 1,050 runs and a surprising result: small local models can use tools remarkably well—until the obvious next step fails.

local-llmdotnetmeasurementagents

Squeezing the juice

How many things can an 8GB card do at once? Fewer than it will let you ask for. In this post I benchmark parallelism in a local llm

local-llmdotnetmeasurement

What the model was thinking

Twenty times the tokens to reach the same answer.

local-llmdotnetmeasurement

What the model actually saw

Four documents, one summarisation, and an answer that took a while to look wrong.

local-llmdotnetmeasurement