Seth Juarez
sethjuarez.com
Seth Juarez
@sethjuarez.com
I work in AI at Microsoft and GitHub. I like Machine Learning and the hot Mexican tamarind candy. Married to the beautiful Riva Juarez.
The smallest bridge from a model to your code is one word. Make it answer BOOK or CANCEL, nothing else. Now `if reply == "BOOK"` works. A paragraph of intent becomes one token your code can branch on. The seed of tool use.

sethjuarez.com/posts/models...
September 15, 2026 at 7:19 PM
Not as new as the hype sounds. Shannon played a guessing game with language in 1951, and Rosenblatt built the perceptron in 1957. Same nudge toward less wrong. We finally got the scale to make it sing.

sethjuarez.com/posts/how-th...
September 14, 2026 at 7:31 PM
The thing AI is actually good for, at least for me: a rough first draft I get to argue with. I do better work when something pushes back.

sethjuarez.com/posts/scribb...
September 11, 2026 at 7:38 PM
The thesis. A model has no agency. Agency is intent plus action. A model can turn your words into intent, a word or a structure. What it can't do is act. It emits tokens and stops. The doing happens in the runtime.

sethjuarez.com/posts/models...
September 9, 2026 at 7:31 PM
How LLMs learn, in one breath. Feed it the internet, hide the next word, let it guess, check how wrong it was, nudge it less wrong. Do that a few trillion times. Grammar and reasoning just fall out the side.

sethjuarez.com/posts/how-th...
September 8, 2026 at 7:19 PM
The Luddites weren't anti-technology. It started as a labor movement, workers defending their trade, serious enough that Lord Byron spoke for them in Parliament. We remember it wrong.

sethjuarez.com/posts/scribb...
September 7, 2026 at 7:35 PM
How does a next-token guesser write paragraphs? A loop. Guess a token, glue it on, feed it back, guess again, until it hits a "done" token. That's autoregression, the engine under every chatbot you've used.

sethjuarez.com/posts/how-th...
September 4, 2026 at 7:18 PM
Post two is up. The model doesn't have agency. It just emits tokens. The agent does, because the agent is the model plus a runtime. Watch the handoff happen, one shape at a time.

sethjuarez.com/posts/models...
September 3, 2026 at 7:16 PM
"Just learn a new skill" is what we tell people about AI now. Someone handed wool workers the same line in 1786, as machines took their jobs. They weren't impressed either.

sethjuarez.com/posts/scribb...
September 1, 2026 at 7:40 PM
A language model does exactly one thing. It guesses the next token. Not the answer, the next token, then it stops. Everything we call "agentic" is scaffolding around that one move. Still amazes me it works.

sethjuarez.com/posts/how-th...
August 31, 2026 at 7:35 PM
Found a petition from 1786 begging Parliament to ban a machine for killing jobs. Swap in "AI" and it's eerily close to today's headlines. We've been doing this for 240 years.

sethjuarez.com/posts/scribb...
August 28, 2026 at 7:39 PM
New series on how AI agents actually work, starting from the plumbing instead of the demos. Post one climbs all the way down to the one dumb thing a model actually does. It guesses the next word.

sethjuarez.com/posts/how-th...
August 26, 2026 at 7:16 PM
The first industrial revolution made muscle cheap. This one is making thinking cheap. Still not convinced that's the bad news everyone assumes it is.

sethjuarez.com/posts/scribb...
August 24, 2026 at 7:40 PM
I haven't written anything in about six years, so naturally I came back with a rant about 240 years of people trying to ban machines. anyway, new post.

sethjuarez.com/posts/scribb...
August 20, 2026 at 7:30 PM
Cinco de Mayo on a Taco Tuesday. The stars have aligned on this, the most beautiful of days. Take a moment to bask in the gloriousness of what today means and how it can shape your life moving forward.
May 5, 2026 at 10:48 PM
In an effort to start writing things down again, I took a baby step and wrote down a bunch of ideas of things I might turn into posts. What should I write about next? sethjuarez.com/ideas/
Ideas - Seth Juarez
Vote on what I should write about next!
sethjuarez.com
April 23, 2026 at 7:10 AM
Duolingo needs to chill out
December 9, 2025 at 6:47 AM
компромат
August 16, 2025 at 12:34 AM
This.
I want to reiterate my deeply held belief. One of the biggest mistakes we are making with this tech is anthropomorphizing it and treating it like it is actually "reasoning". It's not doing that. And it cannot be held accountable. It's a machine.
July 21, 2025 at 5:34 AM
Reposted by Seth Juarez
Ready for a great explanation of agentic AI?

@SethJuarez.com talks on .NET Rocks at www.dotnetrocks.com/details/1957 about what's actually going on under the hood - and how you can take advantage of it!
.NET Rocks!
.NET Rocks! is a weekly talk show for anyone interested in programming on the Microsoft .NET platform. The shows range from introductory information to hardcore geekiness.
www.dotnetrocks.com
July 3, 2025 at 3:04 PM
I have ideas!!
Bluesky's firehose is a treasure trove of public data for researchers and developers, and it's completely free. Check out our developer docs: docs.bsky.app
November 23, 2024 at 6:25 PM
Reposted by Seth Juarez
November 17, 2024 at 8:06 PM
?
November 6, 2024 at 7:44 AM
Deleted the Twitter app - what a cesspool it’s become…
October 23, 2024 at 1:02 AM
I think about the Roman Empire every day
September 23, 2023 at 5:52 PM