Buenas! Hace más de un año que venimos trabajando en @afippi_ar y hasta ahora contamos bastante poco. Así que quería mostrarles qué estamos haciendo y por qué. Va hilo 👇
@korencavs@DamianCatanzaro@papa_de_3_ Vi tu perfil, vos te dedicás a investigar sobre AI safety? Sería tremendo que te mandes un post explicando un poco porque hay poco y nada de info (en el mainstream) circulando de esto!
I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives. More thoughts below.
Para mi tenes dos alternativas:
- Construir una tabla en la DB. Beneficios: in-house, cero latencia, no tenes que conectarte con un third party.
- Usar un servicio externo: cloudflare, posthog. Si no lo tenes conectado ya, es mas costoso.
Personalmente uso posthog para cuando la latencia no es un problema, y sino uso un servicio interno.
Quick Superlogical demo to end the week. This demo is just of the basic functionality, but I want to highlight just how FAST it is. There's a WHOLE lot more functionality already present and coming but I wanted to keep the demo short. But seriously, check out that speed.
I'm showing the macOS app here and I get asked a lot so let me just say up front: its not macOS only. We're still figuring out exactly what platforms will be stable enough for the initial public release, but we're working on others. In particular, the web interface is very functional but I'll demo that another time (or someone else will).
This is also all showing off the architecture I previously talked about for terminal multiplexing which is significantly different from other mainstream multiplexers: this is all a custom binary protocol where the server is maintaining N replica distributed terminal state machines. It works!
Tons of hard work going into this by the team @almonk@dizzyup@pearkes. Hope we can bring you something you can use soon. ❤️ Happy to answer questions in the replies.
Empecé a trabajar con mi clon open source de exe (micro vms por agent) y no es tan fácil. No sólo el soporte de @orca_build a estas tools es limitado, sino que lograr que funcione rápido es bastante complicado. Kudos al equipo de @exedev por lograrlo. TBD a donde llego
@orca_build@exedev Basically what I have failed to do so far with the new per-workspace-env is control them with the CLI. This blocks my skill /delegate-to-worktree where I plan in my main branch and then delegate to a different worktree.