Podría oír esta canción en bucle por horas. Lo hacía hace años, lo hago hoy, y probablemente lo haré siempre.
La Segunda Oportunidad https://t.co/zLKQlJDrbw vía @YouTubeMusic
@akoskm No, but it was pretty decent, imo. I tried it on a mini with 24GB; I figure the more RAM the better.
If I can get "limitless" tokens, that'd be great. Token availability is my main bottleneck. Gemini CLI barely gets me through my daily work, and Go barely through the weekend.
@avazqa Just thinking online. I've coded with LLMs since ChatGPT launched. Coding agents are a huge boost, but only if you follow specific patterns religiously: ask for a plan first, without changing a line of code. It's so effective, those two actions need their own marketing buzzwords.
@Anaya_sharma876 All of them. The problem is usually the prompt.
A combination of all of them yields the best results.
Don't just prompt-change code away. Prompt-plan it first. It's orders of magnitude better.
Our biggest breakthrough in efficiency yet, the Framework Laptop 13 Pro with 20 hours of battery life. In Graphite.
Linux-first with options for Ubuntu pre-installed. Featuring Intel® Core™ Ultra Series 3 processors, LPCAMM2 Memory, a new haptic touchpad, and a touchscreen display.
Pre-orders for the Framework Laptop 13 Pro open now: https://t.co/88vOj9duM1
@charliesbot Tengo la impresión de que estos modelos están teniendo problemas de escalabilidad. Me pasa lo mismo con Gemini CLI.
El otro día espere 5 minutos por unos simples cambios a una consulta SQL.
Now that we're soon running out of 32-bit namespace for transfer IDs at @Wise, the engineers are annoyed with me choosing int over long when I wrote the first lines of code in 2010.
But why don't they appreciate the $17 of savings in storage cost over years!? 🤷
LIVE: They are coming home.
Watch as the Artemis II crew returns to Earth, splashing down at around 8:07pm ET (0007 UTC April 11). https://t.co/n3vZE2rcFv