Rafael Almonte retweeted
LIDOM 2026-27 leaders in my pitch models (min. 100 pitches)
- Pitching+: Robinson Martínez 139
- Stuff+: Michael Arias 139
- Location+: Bryan Rodriguez 141
- Command+: Bryan Rodriguez 141
- 100 = league average.
More details in a thread coming soon... 🧵
Source: MLB
Rafael Almonte retweeted
Can the count and the batter's hand tell you what pitch is coming next?
We trained models on 2.85M MLB pitches (2023-26) to predict the next pitch type, then tested them on 301k pitches from Jul-Sep 2026.
What we found:
Rafael Almonte retweeted
Replying to @aguilascibaenas
@aguilascibaenas va 2-6 y se dice que tiene el peor roster de la LIDOM.
Revisé cada batazo, cada apertura y cada jugador para encontrar sus puntos débiles de verdad.
Spoiler: el roster no es el problema.
Abro hilo 🧵:
1/14
Rafael Almonte retweeted
¿A qué nivel del béisbol profesional se parece más la @LIDOMRD?
Primer paso: ver quién juega.
Cruzamos cada aparición al plato y cada bateador enfrentado en la LIDOM, de 2021-22 a 2025-26, con dónde jugó ese jugador el verano anterior.
Abro hilo:
1/8
Rafael Almonte retweeted
1/10 🧵 ¿Qué cambió en la @LIDOMRD en las últimas 5 temporadas? Más carreras, abridores más cortos y un Escogido bicampeón que se transforma en el RR.
Un hilo con datos de MLB (2021-22 a 2025-26) 👇
Muestras pequeñas: esto mide lo que pasó, no la calidad del equipo o jugador.
☕ How Java programs can reach close-to-native performance for matrix-multiply computations on hardware with accelerated MMA support, such as NVIDIA GPUs
☕ How the same Java Tensor API can be mapped across different parallel programming models and vendors while remaining portable for source code and runtime scheduling parameters
This article examines both: social.ora.cl/6011BEbmLc
Rafael Almonte retweeted
Who said you need Python for ML? ☕️🤖
@jralmontec and I, benchmarked Logistic Regression across 4 major Java ML libraries, evaluating accuracy, ceremony, solvers, and ergonomics:
• Smile • Tribuo • Weka • DeepNetts (JSR 381)
Breakdown below👇
theitdojo.substack.com/p/log…
Rafael Almonte retweeted
New post is live on The IT Dojo! 🥋
@jralmontec and I, compared implementations, ergonomics, and benchmarks across Smile, Tribuo, Weka, and Deep Netts using the exact same dataset.
theitdojo.substack.com/p/log…
Rafael Almonte retweeted
¡Keynote de apertura en #JConfDominicana2026!
Con base en su experiencia en entornos empresariales y su rendimiento de élite en deportes internacionales, Francisco explora cómo las organizaciones pueden:
Rafael Almonte retweeted
“En RD no hay personal calificado.”
…Proceden a contratar una multinacional que termina subcontratando exactamente el mismo capital humano que descartaron inicialmente, pero ahora facturándoles en dólares, con slides en inglés y un “know-how” que casi nunca aparece. 😜😝
Rafael Almonte retweeted
NEW POST: Tribuo: Machine Learning That Speaks Java open.substack.com/pub/theitd…
cc @jralmontec
Rafael Almonte retweeted
Freddy Peña @fred_pena Vaadin Champion y miembro del staff de la comunidad Java de República Dominicana, te invita a asistir al evento más importante de tecnologías Java en el caribe.
#Java #JUGEvents #JVM #LatamJUGs #Conecta #Aprende #Evoluciona
TIL: "Chaos engineering is a discipline that aims to improve confidence in fault-tolerance mechanisms through experiments such as deliberately injecting faults" (DDIA, Martin Kleppmann)
1
39
Spring: The Documentary arrives 7th May! 🍃
Spring didn’t start as a framework, it started as a reaction to complexity in enterprise Java.
What followed was a movement that redefined how modern applications are built, from Spring Boot to the cloud era.
This is the story behind one of the most influential technologies in software.
"When operating on large volumes of data, rather than transferring the data from storage to a separate machine that processes it, it can be faster to bring the computation to the machine that already has the data" - Martin Kleppmann, DDIA
1
1
38
@Brayanmnz_, this takes me back to our “OK, But What About Predictive AI?” talk:
"Bring the model to the data, not the data to the model"
1
26
Rafael Almonte retweeted
HOY!!
7:00 PM hora 🇩🇴
Hablemos sobre la IA predictiva en Java.
youtube.com/live/pmUR2_kfSa8…
Excited to share that The IT Dojo is live 🚀
I’m building this blog with my great friend (and usual co-speaker), @Brayanmnz_. We’ll be focusing on Java, Machine Learning, and real-world systems.
theitdojo.substack.com/p/wel…
Rafael Almonte retweeted
🚀 Ready to build AI-powered Java applications? Join AI4J™ on April 14, 2026. Link: bit.ly/4vnqv5t @Brayanmnz_ and @jralmontec, members of our community, will be leading a session. Don’t miss out—register now and take your Java and AI skills to the next level!

ALT AI4J™ – The Intelligent Java Conference and learn from industry experts as they share practical techniques for building production-ready AI systems with Java. Whether you're just exploring AI or scaling enterprise applications, this event will equip you with actionable insights to implement immediately.












