CT No.76 [rerun]: Platform like a professional
How to choose a content business model and platform software
newsletter-archive
CT No.233: Adamantium skeleton
The storytelling tradition of SEO strategies and annual reports
CT No.232a: It's time to send the correct link.
In many email clients, that Spotify embed didn't work (although they work fine if you view in browser. But if you don't want to work even that hard, here are the playlists as boring regular links instead. * Best songs of 2024 * Christmas Goodies Have a lovely...
CT No.231: Call me a square
We must remember: the internet is optimized to make us angry. But, begrudgingly, I kinda like LinkedIn.
CT No.230: Forecasting content impact
A step-by-step method to proving the value of your 2025 content plans
CT No. 228: Candy corn, peanut butter cups, Milky Ways, and Smarties
How to use a measurement model to understand the effectiveness of content
CT No.245: Billy Joel mathletics
Query fan-out is a new term for what's long been a bedrock of keyword-based language processing: the nouns are central to understanding the user's intent.
CT No.244: Explicating "attention" in LLMs
The words we publish and hold up for peer review remain the best representation of our brains at work in the digital world. A published paper is the best way to look closely at the foundational assumptions of LLMs. And those begin with pop culture.
CT No.243: Disambiguation, sliding doors, hallucinations, and madeleines
Transformers take static vector embeddings, which assign single values to every token, and expand their context, nearly simultaneously as they process the context of every other word in the sentence. But who cares, let's listen to a pop song!
CT No.242: What's your vector, Victor?
How to understand tokens and vector embeddings, for word people.
Processing your application...
Please check your inbox and click the link to confirm your subscription.
There was an error sending the email