Gaston Milano Millan

De paso por acá, siempre pensando que lo mejor está por venir más allá de todo.

[Gaston Milano Millan @GMilano]

With this level of observability, identifying bottlenecks becomes straightforward.

Yes, agents can analyze all of this data.

But humans still understand systems best through visual feedback.

Watching tokens flow, costs accumulate, tools execute, and time unfold across a Loop gives you an immediate understanding of what's happening, and where to optimize next.

[Gaston Milano Millan @GMilano]

Tools

[Gaston Milano Millan @GMilano]

It’s almost like a new reserved keyword 🙂. At least in Claude Code, the color is blue. Anyway, before creating a flow, Claude first figures out whether you’re actually trying to create an automation or not. In some trivial cases, it can already recognize the intent behind what I wanted semantically.

[Juan J. Moreno @JOTA_uy]

🇺🇾 Uruguay es el país de Sudamérica con mayor índice de uso de IA, según el informe global de Anthropic.

Índice 1.21 — usamos IA más de lo que nuestro tamaño haría prever. Y no para el ocio: desarrollo web, código, sistemas. Talento y uso real.💡

🔗 https://t.co/PkX3FM9cPr #IA

[Gaston Milano Millan @GMilano]

@cursor_ai blog on indexed regex search lit the spark . fast-grep watches any directory, kept fresh by a FS daemon. MIT, Rust.

At @Globant we build agents, and the tools that make them fly.

https://t.co/hBbQJkY8D8

[Gaston Milano Millan @GMilano]

We made grep really fast. fast-grep on the Linux kernel (81k files, M1 Pro): 6–25× faster than ripgrep, 2–10× faster than ugrep , faster than every indexed grep we measured. Sub-200ms per query after a one-time index build. 🧵

[Gaston Milano Millan @GMilano]

Why does this matter? Coding agents call grep on every reasoning step. Each call blocks the next thought. Across a session, slow search compounds into minutes of dead time. It's probably the single biggest latency leak in any agent harness.

[Gaston Milano Millan @GMilano]

Salud a “La escuelita” fue el cuadro que amo mi viejo y del que mayores recuerdos tengo en la “B” colándome en el Roberto para poder ver a Racing, desde algún lado estarás viejo levantando algo que en vida no pudo ser . Me pone muy contento por todo Sayago , Gracias Racing querido quién sabe las vueltas de la vida no encuentre algún día a Santi vistiendo tus colores , salud campeones .

[Gaston Milano Millan @GMilano]

And we had a great time, even without AI, an incredible moment to learn, connect, and genuinely enjoy ourselves.

[Gaston Milano Millan @GMilano]

Neither Claude nor Codex nor any AI has invented what’s coming next yet. AI is deeply involved, but it’s not the spark.

Not the latest protocols, not the newest ideas, not even the combinations that might look trivial in hindsight.

Which is exactly why we need to spend real time with each other. To connect, to debate, to explore.

Things are moving fast, but there’s still a lot of engineering to master, research to stay close to, and systems to deeply understand.

That’s why we came to Seattle, to spend time with the people shaping what’s next.

Huge thanks to the entire #AWS team for an incredible week. A lot to build together.

#AWSEBC

[Martin Migoya @migoya]

Impressive work analyzing 45 of my earnings calls — probably more carefully than some Wall Street analysts covering us. The pattern your sensors picked up is real: we didn't pivot to AI, we rebuilt the entire company around it. 173,000 transcripts and you found us. That's your system working. https://t.co/J1KfR8iuRE

[Gaston Milano Millan @GMilano]

Hey @Railway Running multiple AI prototypes on Railway and got the entire account banned due to a “phishing” flag , unclear which project triggered it.

Enforcement matters, but systems should be proportional: isolate the issue, allow remediation, and move checks earlier in the flow.

Otherwise you’re breaking builders, not protecting users.

By the way: no human support, no agentic support either.

[Gabriel Simonet @gabrielsimonet]

The trustworthiness of deterministic code generation, thanks to Symbolic AI, meets the productivity of Generative Coding Agents to build mission-critical, enterprise systems you can evolve with trust. Congrats to the amazing @GeneXus by @Globant team!

[Martin Migoya @migoya]

Despite AI, this is exactly what we’re seeing in the market, Aaron! The lower friction to build software is exploding demand for custom solutions, UI migrations to smarter interfaces, legacy enterprise replacements, and full-area automations that before were not economically feasible or even possible in some ocasions. Jevons paradox in full effect🔥

[Guibert Englebienne @guibert]

Decir que la IA va a hacer desaparecer a los ingenieros de software es como decir que la Thermomix hizo desaparecer a los chefs.

Las herramientas cambian.
Los oficios evolucionan.
Los buenos profesionales se vuelven más poderosos.