Sign in

Seth Juarez

@sethjuarez.com
3.6K followers 487 following 60 posts

I work in AI at Microsoft and GitHub. I like Machine Learning and the hot Mexican tamarind candy. Married to the beautiful Riva Juarez.

PostsRepliesMedia
Seth Juarez @sethjuarez.com · 28/09/2026
A model only emits text. Shape it like a function call and you get tool use. It returns { name: "book_flight", ... }. Your runtime calls the real book_flight(). The model just made text; the booking happened in your code. sethjuarez.com/posts/models...
000
Seth Juarez @sethjuarez.com · 21/09/2026
A model only hands your code text. Force it into a shape your program can read. Ask for a small structure, not prose. { destination, date, time }. It reads a messy sentence and hands back named fields your code acts on. sethjuarez.com/posts/models...
010
Seth Juarez @sethjuarez.com · 18/09/2026
A model that browses is still just guessing the next token. The whole art of "agentic" is arranging the world around that guesser so its output means something to a program. Next up, shapes code can trust. sethjuarez.com/posts/how-th...
010
Seth Juarez @sethjuarez.com · 15/09/2026
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...
011
Seth Juarez @sethjuarez.com · 14/09/2026
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...
000
Seth Juarez @sethjuarez.com · 11/09/2026
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...
031
Seth Juarez @sethjuarez.com · 09/09/2026
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...
000
Seth Juarez @sethjuarez.com · 08/09/2026
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...
001
Seth Juarez @sethjuarez.com · 07/09/2026
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...
010
Seth Juarez @sethjuarez.com · 04/09/2026
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...
000
Seth Juarez @sethjuarez.com · 03/09/2026
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...
000
Seth Juarez @sethjuarez.com · 01/09/2026
"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...
010
Seth Juarez @sethjuarez.com · 31/08/2026
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...
140
Seth Juarez @sethjuarez.com · 28/08/2026
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...
000
Seth Juarez @sethjuarez.com · 26/08/2026
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...
030
Seth Juarez @sethjuarez.com · 26/08/2026
OK! Took your notes and augmented them a bit for the next post - let me know if it's better: www.sethjuarez.com/posts/how-th...
sethjuarez.com
How the Machine Guesses the Next Word
Before we can talk about agents, look at what a large language model actually does. It does exactly one thing: guess the next token. Everything agentic we build later stands on that single, humble mec...
000
Seth Juarez @sethjuarez.com · 24/08/2026
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...
000
Seth Juarez @sethjuarez.com · 22/08/2026
For me, it's more important to get the ideas out as fast as I can (I have a lot). I don't mind the LLM smoothed vernacular so long as the ideas are clear - ideas which are mine and are in fact "load bearing." Thanks for chiming in though - suggestions on how you eliminate those kinds of LLMisms?
100
Seth Juarez @sethjuarez.com · 22/08/2026
Not rude at all. Tell me more! Did what I was trying to say get overpowered by the AI assist?
100
Seth Juarez @sethjuarez.com · 20/08/2026
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...
232
Seth Juarez @sethjuarez.com · 05/05/2026
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.
050
Seth Juarez @sethjuarez.com · 24/04/2026
Oh! It’s my own thing!
030
Seth Juarez @sethjuarez.com · 23/04/2026
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/
sethjuarez.com
Ideas - Seth Juarez
Vote on what I should write about next!
140
Seth Juarez @sethjuarez.com · 09/12/2025
Duolingo needs to chill out
140
Seth Juarez @sethjuarez.com · 16/08/2025
компромат
071
Seth Juarez @sethjuarez.com · 21/07/2025
This.
061
Reposted by Seth Juarez
Richard Campbell @richcampbell.bsky.social · 03/07/2025
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!
dotnetrocks.com
.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.
072
Seth Juarez @sethjuarez.com · 18/02/2025
I'm not sure this an accurate take. Happy to learn more about this take though!
000
Seth Juarez @sethjuarez.com · 10/02/2025
I remember saying this exact thing….
070
Seth Juarez @sethjuarez.com · 07/12/2024
Yes and take my wife
070
Seth Juarez @sethjuarez.com · 25/11/2024
How does this work?!?! I need to put it on my site ASAP
190
Seth Juarez @sethjuarez.com · 23/11/2024
I have ideas!!
2110
Seth Juarez @sethjuarez.com · 23/11/2024
It’s because I moisturize of course
150
Seth Juarez @sethjuarez.com · 19/11/2024
But I tried to be nice about it 🤣
110
Reposted by Seth Juarez
Sarah Young @sarahyo.com · 17/11/2024
Ignite hosts assemble! (Hurry up @donasarkar.bsky.social ) @karuana.bsky.social @sethjuarez.com #MSIgnite
4564
Seth Juarez @sethjuarez.com · 06/11/2024
?
130
Seth Juarez @sethjuarez.com · 23/10/2024
Deleted the Twitter app - what a cesspool it’s become…
3331
Seth Juarez @sethjuarez.com · 03/10/2024
Same
230
Seth Juarez @sethjuarez.com · 02/10/2024
you should renew it - because you never know right?
020
Seth Juarez @sethjuarez.com · 23/09/2023
I think about the Roman Empire every day
020
Seth Juarez @sethjuarez.com · 09/08/2023
Looks like Build version: 1.43.0 (2); Platform: ios
000
Seth Juarez @sethjuarez.com · 08/08/2023
Bluesky is great but this bothers the heck out of me
130
Seth Juarez @sethjuarez.com · 09/05/2023
If you're wondering....
060
Seth Juarez @sethjuarez.com · 07/05/2023
who has an AI question?
130
Seth Juarez @sethjuarez.com · 04/05/2023
OH SNAP! She's awesome!
010
Seth Juarez @sethjuarez.com · 03/05/2023
Hey friends! I did a thing on prompt engineering: www.youtube.com/watch?v=2sEujkZ79E4
youtube.com
010
Seth Juarez @sethjuarez.com · 02/05/2023
ugh - some of these are terrible takes
000
Seth Juarez @sethjuarez.com · 01/05/2023
As promised - here's the code I showed during the #AIShow that gets into the basics of prompt engineering: github.com/sethjuarez/storechat Feel free to shoot me any questions!
063
Seth Juarez @sethjuarez.com · 01/05/2023
010
Seth Juarez @sethjuarez.com · 01/05/2023
Hey friends! I'm doing a live show about how ChatGPT works and some prompt engineering basics! Come heckle me! (Starts in 20m): www.youtube.com/watch?v=2sEujkZ79E4
031