We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

😢 ahí se va una de las mejores cuentas que X supo tener

🙏

Y yo que me sentía el peor padre porque ya lleve dos veces al pibe al jardin sin la mochila 🤣

Harnesses often get dismissed as just scaffolding, just prompt engineering, and not real research. But that couldn't be farther from the truth. The same model weights that score 30% on ARC-AGI score 95% with a better harness. So we gathered a group of researchers and founders working at the frontier to do a deep dive into the state of harnesses. We cover how we got to this point, the case for making your harness as expressive as possible, and what YC learned building an agent for every employee in the company. 00:00 - @FrancoisChauba1: Why harnesses matter 04:27 - Building an auto-researcher by accident 07:13 - A five minute history of harnesses 13:56 - Self-improving harnesses 18:35 - @sethkarten: Prime Agent, a self-improving RLM harness 21:50 - Context as an L1, L2, L3 cache 24:51 - From Turing machine to von Neumann computer 28:33 - Messaging between agents 30:04 - ARC-AGI results 33:09 - Emulator Bench and GPU kernels 37:30 - @JonSaadFalcon: OpenJarvis, personal AI on personal devices 38:26 - How far behind are local models 39:21 - The five primitives of a personal AI stack 42:47 - Letting cloud models optimize your local stack 43:53 - 800x cheaper than the cloud 45:58 - @josh__france and @jbellregan: QM, YC's agent harness for work 47:29 - A history of YC's internal agents 49:24 - OpenClaw and a fleet of 50 agents 51:04 - Pulling the brain out of the sandbox 54:43 - Letting the agent choose its own sandbox and model 57:16 - The grind tool: budgets on goals 58:50 - Agents don't understand social context

In the age of AI with less code more judgment and more flowers.

Se viene la invasión de calamares al Maracaná 🏟️⚽Platense va por la hazaña ante Fluminense 🔥 Fluminense vs. Platense | Mirá #LibertadoresEnTelefe Próximo martes a las 18.45hs con @giraltpablo y @jpvarsky 📺

Este chabon quiere ganar la libertadores con Platense es un genio Te quiero mucho Palermo

GLM-5.3 is now open-weight. Our most capable model for agentic coding and cyber defense is now available to download, run, and customize. Weights: huggingface.co/zai-org/GLM-5… Tech blog: z.ai/blog/glm-5.3

Vivo preguntándome cómo podemos hacer más, automatizar más e ir más rápido con IA. Pero cada tanto también vale frenar intelectualmente (no tecnológicamente, no es posible) y preguntarnos hacia dónde estamos yendo gatesnotes.com/a-turbulent-a…

😢

Lo veo más como una expresión de deseo del mercado que como una realidad. 9 de cada 10 devs/pms/ux/etc que conozco no están en condiciones de convertirse en product engineers, fdes, ai plats. Son roles importantes y que ganarán importancia pero escasos.

Platense es el equipo en el mundo 🌍 que menos tiempo (8 años) necesitó desde la tercera categoría (2018) para lograr todo esto: ✅ Ser CAMPEÓN en Primera División (2025) ✅ Jugar su PRIMER torneo internacional (2026) ✅ Estar entre los 8 mejores del continente 👉 Supera al Ipswich Town 🏴󠁧󠁢󠁥󠁮󠁧󠁿 que estuvo a un solo partido de conseguirlo (cayó ante el Milan 🇮🇹 en 8vos de la Copa de Europa en 1963, 6 años después de haber estar en la 3ra categoría (1957)

🧩 DeepSeek Harness v0.1 is now available in Developer Preview! 🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT license. 🔹 Powered by the Cordis meta-framework, DeepSeek Harness is an agent harness built around one core idea: Everything is a plugin. Models, tools, skills, sessions, sandboxes, filesystems, loops, orchestration, and UI are ALL implemented as plugins, and can be mixed, matched, replaced, and extended. Try it now! github.com/deepseek-ai/deeps…

El CoT estaba cifrado. Pero otros modelos podían leerlo. Muy buen paper sobre cómo convertir modelos en "decryption oracles" y extraer reasoning, secrets y PII de traces supuestamente opacos

We just launched Xirp, a vendor-neutral agentic development environment. One place to manage agent sessions across @ClaudeDevs, @GeminiApp CLI, and @OpenAI Codex. 1,300+ @Spotify engineers already use it. Now it's available for you to try. Learn more at xirp.spotify.com.

ARC AGI Explained