eamazaj

[eamazaj @eamazaj]

My motto is "minimum code, maximum functionality.
-J Kubrynski

[Andrej Karpathy @karpathy]

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.

https://t.co/YCvOwwjOzF
Part code, part sci-fi, and a pinch of psychosis :)

[eamazaj @eamazaj]

La verdadera ventaja no es usar IA… es operacionalizarla.

Con skills en Claude (3 niveles de disclosure + YAML + MCP) conviertes prompts en workflows expertos, repetibles y escalables.

De “probar prompts” a diseñar sistemas

[eamazaj @eamazaj]

Estamos entrando en la 3ª era del desarrollo: no escribimos código, diseñamos la fábrica que lo produce. Agentes autónomos en la nube ejecutan, prueban y entregan; el developer define visión, criterios y calidad. Quien aprenda a orquestarlos hoy, liderará el software mañana. 🚀🤖

[Michael Truell @mntruell]

https://t.co/jZKOk8RAsV

[eamazaj @eamazaj]

Lo que cambió en diciembre no fue incremental, fue un salto de fase. Pasamos de “copilotos simpáticos” a verdaderos agentes que ejecutan, investigan, depuran y entregan. Ya no es solo escribir código: es orquestar sistemas que programan por ti.

No es BAU. Es otro paradigma. 💥

[Andrej Karpathy @karpathy]

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow.

Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes.

As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now.

It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.

[eamazaj @eamazaj]

Adapt or atrophy. Change is the only constant — surf it, don’t sink!

[eamazaj @eamazaj]

@NanoBanana generate an image of Ecuador main tourist attractions in comic book style

[eamazaj @eamazaj]

Hoy no es un día cualquiera! 🌟 Zequi acaba de llegar a su 7ª estación en esta gran aventura de la vida. #ElViajeDeZequi comienza un nuevo y emocionante capítulo. ¡Feliz 7º cumpleaños! 🎂🎉 🧩 #7Años

[eamazaj @eamazaj]

El secreto de todas las victorias consiste en organizar lo que no es obvio.

-MARCO AURELIO

[eamazaj @eamazaj]

El que gana tiempo lo gana todo.

-BENJAMIN DISRAELI

[eamazaj @eamazaj]

Si todo parece bajo control, no estamos yendo lo bastante rápido.
-MARIO ANDRETTI

[eamazaj @eamazaj]

Sólo deberíamos intentar ser mejores que una persona: la que fuimos ayer.
-Anónimo

[eamazaj @eamazaj]

Todos los hombres sueñan, pero no todos sueñan igual.

-T. E. LAWRENCE

[eamazaj @eamazaj]

Busca la verdad y encontrarás el camino.

-FRANK SLAUGHTER

[eamazaj @eamazaj]

Busca la verdad y encontrarás el camino.

-FRANK SLAUGHTER

[eamazaj @eamazaj]

La gratitud es el signo de las almas nobles.

-ESOPO

[eamazaj @eamazaj]

Buscamos menos el sentido de la vida que sentirnos vivos.

JOSEPH CAMPBELL

[eamazaj @eamazaj]

No hay amigo más fiel que un libro.
- Ernest Hemingway

[eamazaj @eamazaj]

La intuición de un momento vale, muchas veces, por la experiencia de una vida.
—OLIVER WENDELL HOLMES

[eamazaj @eamazaj]

Un experto es una persona cualquiera que da consejos fuera de casa. —Oscar Wilde

[eamazaj @eamazaj]

El secreto para salir adelante es simplemente empezar. —Mark Twain