Pinned Tweet
I was asked in an interview about talks or public presentations I've given. Thought it might be useful to publish them here. Most of them are in Spanish, but here goes anyway:
1. Modern Data Stack @thedatapub
An attempt to demistify the word "modern" by going through the cycles technology has had for analytics
Carlos Alberto Haro retweeted
🍻 ¡Nuevo Meetup de The Data Pub!
Hace 3 años exploramos el Modern Data Stack. Hoy, con GPT y agentes de IA por todos lados, ¿qué cambió realmente?
🎤 @h1sort regresa con Post AI Data Stack.
📅 21 de octubre | 7 pm CDMX
📍 Presencial + streaming
🔗meetup.com/thedatapub/events…
Carlos Alberto Haro retweeted
Remember that Anthropic (along with ~all other agentic solutions) need this to be ALREADY DONE before using agents on your data
We are entering a new era of discovery now:
openai.com/index/sharing-ai-…
finally
Claude Sonnet 5.5 is out! We wrote a guide for building with it:
• choosing between Sonnet 5.5 and Opus 5.5
• migrating from Sonnet 5 and tuning effort
• using it in Claude Code
claude.dev/blog/building-wit…
Readers added context they thought people might want to know
The reference photograph shown in this video was originally posted by @IceSolst. The photographer stated it was used without credit or permission.
x.com/IceSolst/statu… x.com/IceSolst/statu…
Hoy daré la clase 2: AI en bases de datos transaccionales y analíticas. El curso es gratis y se queda disponible en YT
youtube.com/live/Hme1ezxmvUY…
La clase 1 del curso de IA para datos nos dejó así: 🤯🤯🤯🤯
Si te la perdiste, la buena noticia es que aún puedes ver la grabación y ponerte al corriente antes de las próximas 2 clases.
Es gratis: codigofacilito.com/ia-datos
I can't seem to stop thinking about this specific paragraph
new post: the senior engineer death spiral
sunilpai.dev/posts/the-senio…
a friend just started a big job and asked for some advice. so I braindumped a monologue about a super common failure mode I see with engineers and posted it here, hope it helps whoever it can.
“the delicate art and science of filling the context window with just the right information for the next step”
Carlos Alberto Haro retweeted
Put together some notes on Jev and the new category of system one aka decision models simonwillison.net/2026/Sep/2…
Yes, classifiers existed. BERT, DeBERTa, GLiNER, fine-tuned heads. Most of them were specialized. Pick the labels, train, ship. Changing the rules at runtime meant another training run.
What we did not have was a general-purpose classifier at Terra / Sonnet 5 level intelligence.
You could fake it by asking an LLM for JSON, but that was slow, expensive, and poorly calibrated.
Jev is that missing piece. Labels defined in code, typed answer plus confidence, no extra LLM call.
Classification is not new. What is new is a general-purpose classifier this intelligent, this fast, and this cheap.
Aquí andaremos un rato, pásele a platicar
Lanzamos un nuevo curso en vivo de Inteligencia Artificial para datos.
Te contamos todos los detalles este jueves en nuestro canal de YouTube:
youtube.com/live/W7duPPiWNFs…








































