CT No.248: Robots read text, not subtext
And other insights for developing content in the new era of AI-powered search
newsletter
CT No. 247: For the rage monkeys and the print nerds
A holiday gift guide for the content professionals in your life
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.
CT No.253: Be a model or just look like one
How to join the resistance, even if you're not in Minnesota
CT No.252: A five-alarm fire is not rage-bait.
A plea for help to end the violence in Minnesota
CT No.251: Prioritizing during an extended crisis
An update from Minneapolis
CT No.250: In praise of good trolls
On the smartest SEO and accessibility expert I knew
Processing your application...
Please check your inbox and click the link to confirm your subscription.
There was an error sending the email