Latent Space
A podcast and newsletter interviewing the people building AI infrastructure and products, aimed at engineers rather than investors. A practical way to keep current on where the field is actually going.
Community
AI & Machine Learning
swyx and Alessio Fanelli
Ongoing
All
Free
What it is
Long form interviews with engineers and founders building AI systems, plus written analysis, oriented toward the practical questions of what is being built and what it took.
Why it is worth the time
Most coverage of this field is written for people deciding whether to invest in it. This is written for people who have to build it, which means the conversations get into evaluation problems, inference costs, what did not work and why, and the unglamorous engineering that fills most of the schedule.
How to use it
Background listening rather than study. Its value is keeping a map of the field current so you are not surprised by a technique or a tool that has become standard while you were busy.
Best for: engineers who want to stay oriented without reading launch announcements all day.
Ready to start?
Opens on swyx and Alessio Fanelli in a new tab.
Stuck on something specific?
Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Every session is free; a few slots open each week.
Follow along
New writing, resources and project ideas land here first.