@mmonjasEngineer
Account based inSpain
About this account
- Account based in
- Spain
- Connected via
- Spain Android App
Account-level information from X, not a live location or the device used for a specific post.
Indeed
C is Latin, the root of all modern languages, the whole universe used to speak it.
C++ is French, it’s Latin with fancy rules, used by the elite around the world & in specific circles.
JavaScript is English, everybody speaks it, most speakers speak it poorly and others don’t bother learning another language.
Java is German, it’s verbose, over-complicated and it made me cry several times. I won’t elaborate.
Python is Esperanto, it was created to be so easy everyone could speak it. Its speakers could benefit from a shower once in a while.
Rust is Russian, most speakers have an authoritarian left background and want to spread it worldwide.
The title of this post is a reference to Glyph's Python Packaging is Good Now. I think it's safe to... dev.to/astrojuanlu/python-pa…
Miguel-Angel Monjas retweeted
Not Everyone Has an Inner Voice Streaming through Their Head
The extent to which people experience “inner speech” varies greatly, and the differences matter for performing certain cognitive tasks.
scientificamerican.com/artic…
Miguel-Angel Monjas retweeted
🚨BREAKING: The @Stanford Institute for Human-Centered AI publishes its Artificial Intelligence Index Report 2024, one of the most authoritative sources for data and insights on AI. Below are its top 10 takeaways:
1. AI beats humans on some tasks, but not on all;
2. Industry continues to dominate frontier AI research;
3. Frontier models get way more expensive;
4. The United States leads China, the EU, and the U.K. as the leading source of top AI models;
5. Robust and standardized evaluations for LLM responsibility are seriously lacking;
6. Generative AI investment skyrockets;
7. The data is in: AI makes workers more productive and leads to higher quality work;
8. Scientific progress accelerates even further, thanks to AI;
9. The number of AI regulations in the United States sharply increases;
10. People across the globe are more cognizant of AI’s potential impact—and more nervous.
➡️Read the @StanfordHAI report below.
➡️For more information on AI policy & regulation, subscribe to my newsletter (link in bio).
Miguel-Angel Monjas retweeted
This is a mind-blowing announcement. Mistral AI, the French company that has been fighting tooth and nail to water down the #AIAct's foundation model rules, is partnering up with Microsoft. So much for 'give us a fighting chance against Big Tech'. A 🧵1/8
azure.microsoft.com/en-us/bl…
Miguel-Angel Monjas retweeted
Advanced Retrieval-Augmented Generation (RAG) techniques address the limitations of naive RAG pipelines.
A recent survey on RAG classifies advanced RAG techniques into pre-retrieval, retrieval, and post-retrieval optimizations.
🔗 Paper: arxiv.org/pdf/2312.10997.pdf
My latest article gives an overview of advanced RAG techniques:
🦙 Pre-retrieval includes techniques like sliding windows, enhancing data granularity, adding metadata, or optimizing index structures, such as sentence window retrieval.
🦙 Retrieval includes optimizing the embedding models (e.g., fine-tuning) or advanced retrieval techniques like hybrid search
🦙 Post-retrieval includes reranking or prompt compression.
We also implement a naive RAG pipeline using @llama_index and then enhance it to an advanced RAG pipeline using the following:
• Sentence window retrieval (as a pre-retrieval optimization)
• Hybrid search (as a retrieval optimization)
• Re-ranking (as a post-retrieval optimization)
💻 Jupyter Notebooks: github.com/weaviate/recipes/…
Read more on @TDataScience: towardsdatascience.com/advan…
Miguel-Angel Monjas retweeted
Scientists Are Putting ChatGPT Brains Inside Robot Bodies. What Could Possibly Go Wrong? bit.ly/49nZKT0
The effort to give robots AI brains is revealing big practical challenges—and bigger ethical concerns
Volviendo a #PyData Madrid: meetu.ps/e/MVQ5c/vnP7K/i
Food for thought. "What kind of bubble is AI?", by @doctorow locusmag.com/2023/12/comment…
Nos vemos el miércoles después del megapuente en #PyDataMadrid. Hablaremos de ML para la gestión de deuda y de como fine tunear Stable Diffusion para generar imágenes profesionales de moda. En @ironhackspain (@mataderomadrid). Os esperamos. meetup.com/es-ES/pydata-madr…
Miguel-Angel Monjas retweeted
¿Conoces #LangChain? Es un framework que nos ayuda a desarrollar nuestras aplicaciones basadas en #IAGenerativa de una manera profesional. En el webinar de hoy @oscarfesa nos contará cómo funciona. 🕓 Arrancamos a las 16h 👇
Me ha gustado mucho esta charla sobre #LangChain de @oscarfesa (@paradigmate). ¡Qué crack! youtube.com/watch?v=lY4aGKpD…
Analyzing Data 170,000x Faster with Python sidsite.com/posts/python-cor… | lobste.rs/s/jfmlrc #python #rust
Miguel-Angel Monjas retweeted
💥 ¡Una guía sencilla para seleccionar tu visualización de datos!
🔗 buff.ly/46vhMRR
#DataScience #dataviz #stats #Analytics #MachineLearning #ML #ai #BigData #datamining #programming #RStats #Python #SQL #Excel #DataScientist #technology #tech #iot #java #business
Miguel-Angel Monjas retweeted
🏃Step-back prompting
A new prompting technique from Google Deepmind, can be used to improve RAG results
🦜🔗Now in LangChain!
💬"STEP-BACK PROMPTING is motivated by the observation that many tasks contain a lot of details, and are hard for LLMs to retrieve relevant facts to tackle the task"
Algorithm:
❓Generate a step back question based on the users original question
🌲Do retrieval for both the original question and the step back question
📃Generate an answer based on both sets of retrieved documents
Paper: arxiv.org/pdf/2310.06117.pdf
LangChain Implementation: github.com/langchain-ai/lang…
Con @nodosenlared en el meetup de Madrid MLOps: meetu.ps/e/MxFxs/vnP7K/i
Miguel-Angel Monjas retweeted
¡Recordamos el evento online de R de esta tarde a las 19h!
@R_Hisp
¡Próxima reunión del Grupo de R de Madrid @R_Hisp el jueves 26 de octubre!
@Lluis_Revilla presentará "Un ejemplo de la vida de un paquete: rtweet".
👉Más info y el enlace a zoom: meetup.com/es-ES/grupo-de-us…
Nueva temporada en #PyDataMadrid. Hoy: SQL generado con lenguaje natural y MLFlow para productivización de modelos. ⬇️meetup.com/es-ES/pydata-madr…⬇️
