Estoy construyendo https://t.co/b3n6gmqunJ en público.
Voy a documentar aquí avances, errores, decisiones técnicas, ventas, producto y aprendizajes del camino.
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
Me tomé unas vacaciones de 3 semanas (obligado por una mudanza) de X tech y de mi macbook. Redescubrir que el mundo sigue siendo físico y con interacciones entre personas. Hay mucho allí fuera.
🔴 ¡CLAUDE MYTHOS 5 YA ESTÁ AQUÍ!
Llega por fin la nueva categoría frontera de modelos de Anthropic Mythos 5/ Fable 5.
En números es el modelo más potente jamás lanzado. Incluso mejorando las cifras de Mythos Preview que nos sorprendieron a todos hace unos meses.
Veamos 👇🧵
Hasta aquí mi camino y evolución con la ai:
- Chatgpt
- Abacus
- Gemini
- Opencode terminal
- Claude code terminal
- Claude code desktop
- Codex desktop
- Opencode terminal.
Imagino que algo más cambiará pero hasta ahora estoy muy contento con oc
one of the quotes i find most inspiring on a hard day:
"Whatever your hand finds to do, do it with all your might, for in the realm of the dead, where you are going, there is neither working nor planning nor knowledge nor wisdom"
Ecclesiastes 9:10