So... I told Astra: build me an high quality game, fast paced and fun, to teach me all about git. You are in charge, use blender and 3js, your goal is to complete the game. I'm going to sleep! Let's see!

It quite surprised me that it's IBM doing this :) For anyone lost in the sea of terminologies, principles and needs guidance (like me), I recommend the channel bellow. IBM tutors go through different subjects in a clear and short way. https://youtube.com/@ibmtechnology?si=Mfq1iP1VVHlTf8b2

Hi! 👋 I'm Rob, I was intrigued by this community for builders who love AI! I've been seriously tinkering for over a year now. And recently I've been transitioning more toward working for myself and building stuff. I've also had a company for about six years now. So far leveraging AI to create small web apps with UIs I enjoy using, creating various AI-based building blocks such as taking one file and turning it into something else -- e.g. a text document and turn it into extracted JSON data; or building a "second-brain" for my markdown docs vault and using RAG to discover semantically similar docs in real-time... There is so much to explore...In my 25 years as a software engineer I've never had so much fun in my entire career! 🤓 Also, I have several product ideas I'm exploring and I hope to launch maybe one of them next year! Rather than working for someone else I find it so much more exciting to take the path with more risk, but greater autonomy and hopefully more fun. My objective is to build something that creates value for others that I can at the very least pay my bills and not have to work for someone else. I'm located in the Seattle metro area in the beautiful Pacific Northwest! 🗻🏔️🚣⛅

I started using T3 Code for a very practical reason: the computer in front of me isn’t always the best computer for the work I need to do. My everyday company computer is a Lenovo Legion with an Intel i9-14900HX, 32 GB of RAM, and an RTX 4070 Laptop GPU. It’s a capable machine, but it still has limits. When I’m running an application, compiling projects, reviewing UI, keeping several coding sessions open, and working on multiple things at once, the Legion can quickly become the bottleneck. At the same time, I have legitimate access to other computers that are often sitting idle. At the company, there’s an iMac with only 12 GB of RAM. It’s useful when I need macOS, but it isn’t the machine I would choose for heavier parallel workloads. We also have a dedicated Windows GPU workstation with 64 GB of RAM and a Radeon RX 7600 XT with 16 GB of VRAM. That machine has considerably more headroom for large builds, multiple simultaneous tasks, local models, and GPU-intensive work—especially at night, when nobody else is using it. At home, I also have my personal Linux machine. It has its own role: persistent services, Linux-native tooling, background processes, and projects that make more sense in a Linux environment. Before T3, these felt like separate computers. Every machine had its own files, terminals, dependencies, running processes, and unfinished work. Moving between them meant rebuilding context, copying things around, or trying to make one computer handle everything. T3 Code—and especially T3 Connect—changed that for me. Now I can sit at the Legion and connect to whichever environment makes the most sense for the task. The repository, terminal, dependencies, Git state, and running processes remain on the machine actually doing the work. I don’t need to move the entire project just because I moved to a different desk or opened a different laptop. This means I can review an application’s UI from the Legion while the application itself runs on the 64 GB GPU workstation. I can leave a build or a long-running task working there while I continue something else on my Linux machine. If I need macOS, I can move to the iMac environment without disrupting everything else.

Hi everyone, I would like to share my experience that wasn't too traumatic because it was just 20€. If you use P-Stack with Grok Bot, it often chooses other models other than Grok or Composer. It gives amazing results but... BEWARE that it doesn't use cursor's other models. You have to pay API pricing for extra usage inside cursor. Even if you haven't spent all your limits in cursor, it's just unrelated. I can't be mad with cursor because their customer service is very good. If Ben is a bot, it's the best bot I have ever talked to. I will for sure pay the €20, but it could have been much worse because Grok Bot doesn't show the extra usage. You have to go inside Cursor to see it. Here is their explanation: Other Models vs Grok Bot The Other Models bar is for Cursor when you pick a specific named model (Claude, GPT, Gemini, Kimi, and similar). That is separate from Grok Bot. Grok Bot has its own weekly included usage. It uses first-party models automatically (no model picker), so Grok Bot work does not fill the Other Models bar. Agents and tools you run in Grok Bot (including things like pstack) draw from that Grok Bot weekly included usage first. Shared on-demand Grok Bot and Cursor share one login, one subscription, and one on-demand wallet. When Grok Bot’s weekly included usage runs out, extra Grok Bot usage can continue on that shared on-demand if on-demand is enabled. SuperGrok does not cover on-demand; on-demand is billed on your regular invoices. Your Grok Bot screenshot showing weekly usage still low, with the same on-demand total as Cursor, fits that setup: Other Models / on-demand can come from Cursor named-model usage even when Grok Bot weekly usage is barely touched. For the exact split and every event, use: https://cursor.com/dashboard?tab=usage