Valentino Mórtola

Biotecnólogo | Gerente de @caacorrientes | Becario Fulbright ’26 | MS Data Science @riceuniversity 🇦🇷🇺🇸

Views and information are my own.

[Valentino Mórtola @MortolaV]

Discover Rice: An Extended Campus Tour for Graduate Students https://t.co/6hXJpeoe0l vía @YouTube

[Embajada de EEUU en Argentina @EmbajadaEEUUarg]

¡Argentina a la final y el Empire State se viste de celeste y blanco!

[Valentino Mórtola @MortolaV]

India habilitó la importación comercial de yerba mate argentina https://t.co/ygRdrjXbQK

[Valentino Mórtola @MortolaV]

“MADE IN ARGENTINA”. ¿HAY CRISIS EN EL SECTOR NUCLEAR O LA INVERSIÓN PRI... https://t.co/h93YuDqWUV vía @YouTube

[Valentino Mórtola @MortolaV]

🇦🇷🇦🇷

[Reginald DesRoches @RDesRoches]

Rice returned to @VivaTech with momentum — and made the most of its second appearance at Europe’s largest startup and technology event. During the June 17-20 gathering in Paris, @RiceUniversity introduced seven startups from its innovation ecosystem, unveiled new partnerships with French and German institutions, contributed to global conversations on AI, research and higher education and reinforced the Rice Global Paris Center’s role as a bridge between Houston, Paris and the world. #VivaTech #RiceGlobal

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[Filo.news @filonewsOK]

💬 Eric Weinstein: “¿Argentina quiere salir de la decadencia? Hagan un instituto para salir del sistema solar. ¿O simplemente no lo hacen porque no ven a nadie en Estados Unidos haciéndolo?".

🗣@ericweinstein x @santisiri

[The Economist @TheEconomist]

It is only a matter of time before Texas overtakes California as the largest economy in America. Register for free to learn why https://t.co/MH211B1M16

Illustration: Nicolas Ortega

[Jacob Robinson @JTRobinsonLab]

Thanks to @emilylmullin at @WIRED for taking some time to chat with us about our recent approval to start a clinical trial! Exciting year for #BCI !!

[Valentino Mórtola @MortolaV]

👏🏻👏🏻👏🏻

[Cognition @cognition]

1/ We’ve raised over $1B at a $26B valuation, led by @Lux_Capital, @generalcatalyst, and @8vc.

Our enterprise usage has grown >10x since the start of this year, and our run-rate revenue grew to $492 M.

We launched Devin two years ago as the first AI software engineer. Since then, cloud agents have gone from niche to mainstream, and today they are the fastest growing way to create software.

[Valentino Mórtola @MortolaV]

China moves AI brain implants from trials towards real-world use https://t.co/anQmgPdeNA

[Valentino Mórtola @MortolaV]

Researchers who use hallucinated references to face arXiv ban https://t.co/cU1R7x6tn2

[Valentino Mórtola @MortolaV]

Un orgullo!

[Juan Pablo Valdés @JPValdesok]

Corrientes vuelve a ser sede de la Exposición Nacional de Braford, Brangus, Brahman y Caballos Criollos, uno de los encuentros ganaderos más importantes de Sudamérica. Un reconocimiento al protagonismo de nuestra provincia en la producción, con genética de excelencia y alta competitividad.

[Rice University @RiceUniversity]

Dean @profp_rod leaves a lasting impact on Rice Business and the university community. Thank you for your leadership, partnership and dedication, Peter — and best wishes as you begin this exciting next chapter at @WakeForest.

[Valentino Mórtola @MortolaV]

Comparto la charla del Dr. Alejandro Andersson en el marco de la Jornada de Actualización en Cannabis Medicinal que se llevó a cabo en Corrientes.

https://t.co/9hUpjQK13t… vía @YouTube

[Valentino Mórtola @MortolaV]

🇦🇷🇦🇷

[Adrian Mutto @AdrianMutto]

https://t.co/UAlKDWmSun

[Gustavo Valdés @gustavovaldesok]

Por unanimidad, dimos media sanción al proyecto que presenté para crear la Agencia de Desarrollo, Promoción de Inversiones y Comercio Exterior de #Corrientes, que busca potenciar el crecimiento de la provincia y consolidar una política permanente de atracción de inversiones nacionales e internacionales.

La agencia tendrá representación del sector público y privado, con cargos ad honorem, y fortalecerá la presencia de Corrientes en el mundo para generar nuevas oportunidades y promover el desarrollo de los sectores productivos con mayor coherencia, orden y seguridad jurídica.

[Valentino Mórtola @MortolaV]

Pampa Energía pidió ingresar al RIGI para invertir USD 2.400 millones en una megaplanta de fertilizantes en Bahía Blanca - Infobae https://t.co/H2AAS1u4JQ

[Ant @Antrop_nio]

Así se veía originalmente la Biblioteca Nacional en tiempos de Clorindus Testus

[Valentino Mórtola @MortolaV]

Why Texas Is About to Lead America https://t.co/QDhjSIxk4K vía @YouTube