Alessandro

Been talking to a lot of devs about LangGraph's Postgres checkpointer lately, the tricks each team applies to get it production-ready are always different. Here's how we handled it at @tiendanube: custom TTL, cold storage to S3, and understanding when and where in your architecture you actually need a checkpointer. Shoutout to @hwchase17 @Vtrivedy10 @sydneyrunkle @masondrxy @BraceSproul for the inspo.

I’ll be in San Francisco from May 9-16 for @LangChain Interrupt 🦜 If you’re around, DM me, I’d love to chat about applied AI, agents, and running agentic systems in production :)

Isn’t just what to remember, but when to update it: in the loop or after the fact. A must read by @hwchase17!

I'll be in the Bay Area for most of May and early June, mainly around @Stanford campus but also in SF. would love to meet people in AI and tech while I’m there. If you'll be around, DM me

Ayer estuvimos con @apaolini_ contando un poco sobre cómo utilizamos el ecosistema de LangChain en nuestros desarrollos agénticos en Tiendanube. Gracias @PetralliLucas por permitirnos ser parte de este meetup de la comunidad de LangChain, y a todos los que estuvieron presentes 🦜

Muy bueno ver a @LangChain activando en Argentina. cracks @tadeodonegana y @apaolini_ empujando las últimas tendencias en AI en TiendaNube. Las empresas argentinas están más avanzadas de lo que parece.

For example, we gave Claude an impossible programming task. It kept trying and failing; with each attempt, the “desperate” vector activated more strongly. This led it to cheat the task with a hacky solution that passes the tests but violates the spirit of the assignment.

@HooCrypto @TalentProtocol Sos crack amigo, no tengo dudas que lo mejor está por venir

life update: after 3 incredible years, I’m wrapping up my chapter at @TalentProtocol. During my time there, I worked across product, growth, BD, and marketing, helping position Talent as the reputation layer for builders and creators. Some of the things we achieved together: ▫️Helped launch and grow Builder Score and ranks, one of the largest reputation systems for developers. ▫️Worked closely with leading teams to design builder programs, distributing +$600k to builders ▫️Helped shape go-to-market, positioning, and storytelling around Talent’s products ▫️Contributed to making the Talent API key infrastructure for multiple projects, powering +200M requests -- Talent gave me the chance to turn ambitious ideas into real products. I’m proud of what we built together, and very grateful to the team, partners, and builders I got to work with along the way. I’m taking a few weeks to recharge, reflect, and explore what I want this next chapter to look like. At the same time, I’m open to opportunities across Developer Relations and Growth, particularly with teams where I can contribute in multiple areas and help build from different angles. Excited for what’s ahead.

Muy buen post de @santtiagom_ explicando los diferentes patrones para construir agentes. Recuerdo estar en 2024 con @apaolini_ evaluando durante meses diferentes patrones arriba de gpt4-turbo para un agente de data engineering. Habíamos hecho una arquitectura entera de Supervisor, Router y SubAgents cada uno con su Critic agent para que llegue o1 a fin de año y le haga un outperfom con un par de llamadas 😬 (luego terminamos implementando algo similar sobre reasoning igual, pudiendo elevar la vara) Por eso siempre es bueno tener en cuenta el concepto de lo que es un agente: modelo + harness (contexto, arquitectura y demás).

I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then: - the human iterates on the prompt (.md) - the AI agent iterates on the training code (.py) The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc. github.com/karpathy/autor… Part code, part sci-fi, and a pinch of psychosis :)

@marcoporracin Están haciendo text-to-sql directo o hacen uso de alguna capa semántica intermedia?

Ambos puntos son correctos. Te vas a olap, modelas harías OBT y le das contexto solo esas pocas grandes tablas. La rompe. Ya estamos haciendo que haga gráficos y todo

El próximo viernes 20/2 nos juntamos en las oficinas de @Tiendanube con Anthropic y Platanus, para hacer un evento junto a 25 hackers y crear un proyecto desde 0. 12 hs de desarrollo, 12 horas de foco: 3pm a 3 am. Si queres ser uno de ellos, pedile a tu agente que te registre - build-night.platan.us @Tiendanube + @claudeai + @platan_ventures

SAM3 video tracking is so good yesterday: collect data, train custom object detector, use tracker to estimate object motion - days today: track anything with text prompt - seconds

We hosted another LLM-Native meetup at @lemonapp_ar — a space where we bring together founders, engineers, researchers, and AI enthusiasts building frontier products with llms. Full house again, with 200+ on the waiting list. We dug into real-world technical challenges through 8 talks by 12 experts, sharing insights and practical solutions. @tadeodonegana (& lemon’s team) @ideasrapidas @IvannaAFigueroa @HeyFardo @manuelsoria_ @gptcrosa @shroominic @fpingham Thanks to all the speakers for making it happen, and to everyone who showed up for the energy and value you brought. Big thanks to Lemon for opening their doors to host us, and to Tade for helping organize and curate the content. We’re planning more meetups and growing capacity to keep making space for all the amazing talent pushing this field forward in LATAM. llmnative.dev @PetralliLucas @fpingham