# tags
browse: /categories /series /tags /archive
[ Ai and llms ] Part 2 of 6 3 min read
Prompting ClaudeI'd like to claim I've never taught a model a bad habit by accident. A model learns from every part of an example, including the parts you didn't mean to teach, so here's how to pick them, on one chart. Part two of six.
An introduction to a six-part series on how large language models work, from a network engineer who understands most of it and a little of the math.
[ Ai and llms ] Introduction 3 min read
Prompting ClaudePrompting advice ages faster than the models it was written for, and a lot of what's still online, including my own notes, now backfires. An introduction to a six-part series where the infographics do the heavy lifting.
[ Ai and llms ] Part 1 of 6 2 min read
Prompting ClaudeI used to write prompts the way I wrote change-window emails to the NOC: in capital letters, with the word CRITICAL in them. Eight prompt habits that helped on 2023-era models and backfire on the current ones, on one chart. Part one of six.
A frontier training run is a networking problem dressed up in a math costume. The industry chose the chickens over the oxen, so how do you get 16,000 of them pulling in the same direction? Part three of six.
[ Ai and llms ] Part 2 of 6 9 min read
How LLMs Actually WorkTraining turns roughly 405 billion random numbers into something useful through one boring move: guess the next token, get graded, nudge every number a hair, and repeat. Part two of six.
[ Ai and llms ] Part 1 of 6 11 min read
How LLMs Actually WorkA large language model is an enormous pile of numbers, and everything it does comes from multiplying other numbers by that pile. Part one of six.
[ Ai and llms ] 6 min read
I asked an AI to tidy up my blog repo and it accidentally organized itself into a nine-member development team. I'm releasing that team, free, on GitHub.
[ Infrastructure ] [ Ai and llms ] 21 min read
Data centers are eighty years old and already 99% full. We need considerably more of them, and we're making a hash of deciding where they go.