Francisco Borja

Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet. I really like this approach to personalization in a number of ways, compared to "status quo" of an AI that allegedly gets better the more you use it or something: 1. Explicit. The memory artifact is explicit and navigable (the wiki), you can see exactly what the AI does and does not know and you can inspect and manage this artifact, even if you don't do the direct text writing (the LLM does). The knowledge of you is not implicit and unknown, it's explicit and viewable. 2. Yours. Your data is yours, on your local computer, it's not in some particular AI provider's system without the ability to extract it. You're in control of your information. 3. File over app. The memory here is a simple collection of files in universal formats (images, markdown). This means the data is interoperable: you can use a very large collection of tools/CLIs or whatever you want over this information because it's just files. The agents can apply the entire Unix toolkit over them. They can natively read and understand them. Any kind of data can be imported into files as input, and any kind of interface can be used to view them as the output. E.g. you can use Obsidian to view them or vibe code something of your own. Search "File over app" for an article on this philosophy. 4. BYOAI. You can use whatever AI you want to "plug into" this information - Claude, Codex, OpenCode, whatever. You can even think about taking an open source AI and finetuning it on your wiki - in principle, this AI could "know" you in its weights, not just attend over your data. So this approach to personalization puts *you* in full control. The data is yours. In Universal formats. Explicit and inspectable. Use whatever AI you want over it, keep the AI companies on their toes! :) Certainly this is not the simplest way to get an AI to know you - it does require you to manage file directories and so on, but agents also make it quite simple and they can help you a lot. I imagine a number of products might come out to make this all easier, but imo "agent proficiency" is a CORE SKILL of the 21st century. These are extremely powerful tools - they speak English and they do all the computer stuff for you. Try this opportunity to play with one.

¡Pongamos 100% de aranceles a Colombia y celebremos el doble! Nada que festejar… Qué triste tener que aclarar conceptos tan básicos. Pero ya veo que algunos medios se han subido a replicar sin contrastar. Cualquier persona que haya pasado por una clase de Introducción a la Economía 101 sabe que estos argumentos son una falacia económica. 1- Llevamos 250 años superando el mercantilismo (aunque cada cierto tiempo regresa). Adam Smith (1776) demostró que las importaciones no son una pérdida — son la forma en que una economía accede a bienes que produce con desventaja comparativa. 2- David Ricardo (1817) lo formalizó: el comercio crea valor precisamente porque cada país se especializa en lo que hace mejor. Cuando Ecuador importaba de Colombia, ambos ganaban. Cuando se cierra ese flujo, ambos pierden. Lo que el ministerio reporta como una victoria es una destrucción de valor económico. 3- Las importaciones desde Colombia cayeron 57% (de USD 288M a USD 125M en feb-mar 2026, según datos del ministerio). Eso no es competitividad. Es una economía que compra menos porque le sale más caro. Viner (1950) lo llama desvío de comercio: reemplazar al proveedor eficiente por uno más caro es destrucción de valor, no creación. 4- Contrafactual: la tasa de variación promedio de exportaciones en 2025 fue menor al 0.5%/mes. El overshooting de marzo 2026 (+31% en un solo mes) sale totalmente de tendencia — es el último tren antes del 50% colombiano. Exportadores adelantando embarques (tanto en febrero como en marzo). Sin ese efecto, la balanza de marzo habría sido −USD 6M. Todavía déficit. Incluso con importaciones ya desplomadas. 5- Todo lo anterior sin medir efectos en precios internos, cambio en costos para empresas, efecto en PIB, efectos a mediano plazo en empleo (porque no tenemos datos suficientes aún). Y por supuesto todavía con “solo 1/3” de exportaciones ecuatorianas afectadas por el arancel del 30% de Colombia. Pero con amenaza de subir a 50% para casi la totalidad. Peor aún si comparamos con 2024, cuando gran parte de ese déficit comercial era importación de energía eléctrica. 6-La propia publicación tiene las cifras del impacto negativo en comercio 🇪🇨Exp+🇨🇴Imp 2025 (Feb+Mar) 142m + 288m  = 430 m 🇪🇨Exp+🇨🇴Imp 2026 (Feb+Mar) 188m+125m  = 313 m PERDIMOS 117 millones en comercio bilateral en dos meses. 👉Lo que el ministerio debe hacer es parar la guerra comercial. No celebrar que se destruya el comercio bilateral.

🇪🇨 🔝| Por primera vez en más de 25 años, Ecuador le vende más a Colombia🇨🇴 de lo que le compra. La balanza comercial bilateral volvió a ser positiva⬆️. Entre febrero y marzo de 2026, pasamos de un déficit de USD 145,9 millones a un superávit de USD 62,9 millones. Más detalles👇🏻

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.

Con profunda sorpresa, vemos este oficio circular NAC-DGECCGC26-00000002 de viernes 26, 17H00 Aquí vemos una interpretación al Art. 55 de la LORTI, donde se pone IVA una serie de productos sensibles de la canasta básica que antes no los tenían

Monetary disequilibrium theory is just crude Keynesianism dressed in different vocabulary.

Wow