@iadevsconfi
iAccount based inItaly!
About this account
- Account based in
- Italy
- Connected via
- Web
! X says this location may be affected by a proxy or VPN.
Account-level information from X, not a live location or the device used for a specific post.
Donde la Inteligencia Artificial deja de ser humo y se convierte en código
Santiago, Chile
Joined October 2024
- Tweets34
- Following27
- Followers26
- Likes38
Pinned Tweet
🚀 ¡Bienvenidos a la primera conferencia de IADevs!
Este 9 de diciembre, desarrolladores de toda la región se reunirán en Santiago, Chile, para construir juntos el futuro de la IA en español.
📍 Dónde: Aula Magna @ingenieriaUDD_
Entradas gratuitas: ingenieria.udd.cl/ver-semina…
iadevs retweeted
Our work, "Externalized CPDAG Summaries Improve LLM Causal Deduction," has been accepted to NeurIPS!
iadevs retweeted
Happy to announce that I’ve been promoted to Distinguished Member of Technical Staff at Bell Labs.
Let’s keep grinding!
iadevs retweeted
🐍 New Python package just dropped! Generate Mermaid diagrams in Python. Simple, fast & powerful. 🔥 #Python #Mermaid #OpenSource
iadevs retweeted
¿Han cachado que en Chile nos gusta tirar la talla pero nadie tiene idea de qué chucha nos reímos? Sean bienvenidos/as a DataRisas, el portal de datos del humor chileno.
iadevs retweeted
If you are (or know of) a Master's or PhD student looking for an internship, I am proposing the subject: 'Efficient Structured Generation with Grammar-Aware Sampling Techniques.' dropbox.com/scl/fi/7iwfgc4wa…
If you're passionate about structured generation, feel free to reach out!
iadevs retweeted
New blog post: Force a Qwen model not to use Chinese
alonsosilvaallende.github.io…
iadevs retweeted
How is it possible that a 1.7 billion parameter model succeeds where a model with hundreds or thousands of billions of parameters fails?
iadevs retweeted
The latest release of Litelines supports batch processing for Transformers library.
`pip install --upgrade litelines`
iadevs retweeted
My talk, "Processors for Language Models," at PyData Paris 2025 @PyDataParis is now available. I discuss my personal project, Litelines, as well as common libraries used to transform unstructured data into structured data, Instructor, DSPy, BAML, Outlines, XGrammar, and Guidance.
iadevs retweeted
I gave a talk about structured code generation for domain-specific languages: abstract syntax trees (ASTs), concrete syntax trees (CSTs), deterministic finite automata (DFA), pushdown automata (PA), outlines, guidance, Georges Perec, the usual stuff...
iadevs retweeted
💡Respuestas y generación estructurada en LLMs
Alonso Silva muestra cómo combinar técnicas para extraer datos precisos de información no estructurada.
📅9/11 |🕠17:30 – 18:00 | Online
Nivel intermedio | Datos
🎥Transmisión por youtube.com/@PythonChile
#PyConChile2025 #PythonChile
iadevs retweeted
Doing a slightly better documentation than just the README.md (link to the documentation below). Feeback?
Want to visualize the response format constraints on the LLM when working in @ProjectJupyter ?
Then you might be interested in my new project `litelines`.
iadevs retweeted
😍
Here is a @marimo_io molab notebook to get you started with structured generation (link below)
iadevs retweeted
Here is a @marimo_io molab notebook to get you started with structured generation (link below)
Want to visualize the response format constraints on the LLM when working in @ProjectJupyter ?
Then you might be interested in my new project `litelines`.
iadevs retweeted
Visualize the language model choosing a trajectory response in real-time in @marimo_io notebooks.
Want to visualize the response format constraints on the LLM when working in @ProjectJupyter ?
Then you might be interested in my new project `litelines`.
iadevs retweeted
✅ How to get a 100% Guaranteed Valid Tool Call from an LLM.
It's possible, reliable, and surprisingly simple using `litelines`.
Want to visualize the response format constraints on the LLM when working in @ProjectJupyter ?
Then you might be interested in my new project `litelines`.
iadevs retweeted
✅ 100% guaranteed valid JSON from an LLM?
Yes, it's possible, reliable, and surprisingly simple using `litelines`.
Want to visualize the response format constraints on the LLM when working in @ProjectJupyter ?
Then you might be interested in my new project `litelines`.
iadevs retweeted
Want to visualize the response format constraints on the LLM when working in @ProjectJupyter ?
Then you might be interested in my new project `litelines`.
iadevs retweeted
Charla de @cgarciae88 "Una introducción amigable a modelos de difusión" para @iadevsconf con @aastroza y @sebastiandres