Ya hace unas semanas hubo el boom de Jev. Lo hemos estado usando para ver qué piezas son las más relevantes y qué casos de uso sí que tienen sentido. Para ello hemos creado un curso donde: - Vemos si tiene sentido o no vs un LLM usando evals. - Lo comparamos con sus alternativas (Clef, Kev…). - Entendemos cómo puede hacer un LLM de fallback de Jev. - Implementamos rerank para hacer búsquedas semánticas con Jev sobre embeddings.

Very interesting jetbrains’ new vibe coding IDEA uses pi under the hood for agent orchestration. Might have to try this out! github.com/JetBrains/thinkra…

Anthropic has filed an S-1 registration statement with the SEC related to its proposed IPO. Read more: anthropic.com/news/s1-sec Legal disclaimer: A registration statement relating to these securities has been filed with the SEC but has not yet become effective. These securities may not be sold, nor may offers to buy be accepted, prior to the time the registration statement becomes effective. This post does not constitute an offer to sell or the solicitation of an offer to buy these securities, nor shall there be any sale of these securities in any state or jurisdiction in which such offer, solicitation or sale would be unlawful prior to registration or qualification under the securities laws of any such state or jurisdiction.

Anthropic is now recommending that companies REMOVE unnecessary subagents from their AI systems. This is a pretty significant shift in agent architecture, with their team finding that a single agent equipped with skills can frequently outperform complex multi-agent systems, and one customer seeing roughly 2x faster execution. The emerging rules of thumb: → Skills: Teach the agent HOW to do something, including procedures, expertise, and instructions. → Tools / MCP: Give the agent the ability to DO things through APIs, actions, and live data. → Subagents: Use for parallel work, isolated context, or tasks a single agent struggles with. The interesting part is progressive disclosure. Instead of spawning specialized agents or stuffing everything into a giant prompt, one agent discovers and loads skills and tools as needed. Their advice is to fold existing subagents into the main loop, turn their instructions into skills, expose their actions as tools, and run evals to see if performance holds up. As models have gotten smarter, improving agent architecture is becoming less about what you can add and more about what you can delete. claude.com/resources/article…

type inference from .sql files has been achieved internally ORMs are toast

Lo mejor de esta historia: Javi hizo un proyecto que le llevó a conocer a Guillermo Rauch, y eso acabó convirtiéndole en el empleado #10 de Vercel. Si alguna vez has usado un middleware en Next.js o has comprado un dominio en Vercel, has usado algo que pasó por sus manos. Muchas de las cosas que hoy son los cimientos de Vercel las construyó él. A veces nos metemos con él porque el proyecto se quedó a medias, pero el ROI que le ha sacado es infinito. Es acojonante cómo, simplemente haciendo cosas, pasan cosas.