19/ I am going to repeat it again because it is important. If you assume some finite lifespan, there is a hard and calculable limit to how many things you will ever think or feel. You are not a continuous stream of consciousness, but instead a series of discrete prompts.

24/ Actually I am (and you are) a multimodal model with different limits per mode Vision reaction (no words): 180 rpm. 0 tokens Talking mode: 4 rpm. 300 tokens/minute Reading mode: 1K tokens/minute. Writing mode: 5 to 100 tokens/ minute

34/ What is almost certainly true though is "don't waste them on bullshit" Things you don't want to do. Angry typing to someone you are upset at. All of these are "uses of tokens you are paying for with your actual life and probably you will regret"

1/ On The Time Is Now to get your personal act together A mini-thread, views loosely held. If you are like me, you may do a good job in your professional life but there are quite a few things outstanding in your personal life.

Agency > Intelligence I had this intuitively wrong for decades, I think due to a pervasive cultural veneration of intelligence, various entertainment/media, obsession with IQ etc. Agency is significantly more powerful and significantly more scarce. Are you hiring for agency? Are

Lots of buzz on Claude Code here today. This short course, created with Anthropic, is the best way to learn to use it well. Please enjoy it!

how to leverage coding agents to ship fast:

Here's my enormous round-up of everything we learned about LLMs in 2025 - the third in my annual series of reviews of the past twelve months simonwillison.net/2025/Dec/31/th… This year it's divided into 26 sections! This is the table of contents:

NEW: X HEAD OF PRODUCT Nikita Bier SAYS "CT IS DYING FROM SUICIDE, NOT FROM THE ALGORITHM" - "CT ENDS UP WASTING ALL THEIR REACH ON REPLYING “GM” HUNDREDS OF TIMES AND WHEN THEY FINALLY POST REAL CONTENT LIKE A PROJECT ANNOUNCEMENT, IT ONLY GETS SHOWN TO 3 PEOPLE"

x.com/i/article/2010…

x.com/i/article/2010…

x.com/i/article/2010…

X is flooded with Claude Code content right now. Instead of reading it all, just bookmark/read this one article instead. I filtered down the 1% of content that is actually worth your time. Whether you're a beginner or advanced, you'll extract alpha.

x.com/i/article/2009…

If you get through all of this material, you'll be an ML Engineer (MLE) I'm thinking of leading a study group through this content If you're interested in joining, comment "MLE" below

A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in

x.com/i/article/2016…

x.com/i/article/2027…

I'm excited to announce Context Hub, an open tool that gives your coding agent the up-to-date API documentation it needs. Install it and prompt your agent to use it to fetch curated docs via a simple CLI. (See image.) Why this matters: Coding agents often use outdated APIs and