So Google finally decided to do a live demo and of course THIS is how it started... 🤣
00:00
Ted Werbel
2,230 posts
Ted Werbel
@tedx_ai
building something new agentdesk.ai
- Replying to @tedx_aiWonder if that second phone was an alternative version of the app with everything hard-coded... wouldn't be surprised tbh. There's no way they didn't have a contingency plan...
- Most people have NO IDEA just how VALUABLE Grok 3 DeepSearch is for studying your competitors 🦾💥 Before Grok 3 😔 > Spend big $$$ on social listening tools > Schedule endless customer calls > Try to guess what people actually want After Grok 3 🚀 > Tell grok your idea +
- We now have INSTANT access to all data across X thanks to Grok 3 which has INSANE implications… 💥 Worked with @jelanifuel to build out a Market Research System using Grok + OpenAI Deep Research. Here are the prompts + how it works 👇 1️⃣ Define a rough idea of your elevator
- For anyone struggling with Cursor, here are my favorite rules that will help save you HOURS of time. It will help: ✅ Properly understand, triage & resolve complex bugs ✅ Manage a complex/large codebase ✅ Leverage PRDs effectively ✅ Commit code to Github and submit PRs with
- Replying to @DiarioBitcoinYeah I feel bad for him... that was a rough moment 😔
- These rules will save you HOURS of debugging when using Cursor 🔥🦾 Just say "Debugger Mode" or "Planner Mode" and watch Cursor work its magic 🪄 Full prompt down below ⬇️ Make sure to get BrowserTools MCP as well to FULLY automate analysis of browser logs. Link in bio 👆
- Grok 3 is the ULTIMATE tool to design your next big software project 🔥 Take these prompts & within ONE HOUR, you will have the following done: ✅ End-User Profiles & Personas ✅ Sitemap & Design Doc ✅ User Stories w/ Acceptance Criteria Feed this to Cursor along with tech
- I just built this CRACKED Cursor MCP extension that makes your IDE fully aware of all the logs in your browser. Was struggling with a few issues recently and kept having to copy/paste logs but with this tool you can: ✅ Check all console logs + errors ✅ Analyze network
00:00 - This past week, an anonymous AI researcher released an INCREDIBLY innovative architecture known as Entropix which aims to replicate how OpenAI’s latest o1 model scales inference-time compute - otherwise known as its ability to 'think' before speaking. It’s essentially based on
- Replying to @natemcgradyTry this prompt instead, works like magic 🪄 "Reflect on 5-7 different possible sources of the problem, distill those down to 1-2 most likely sources, and then add logs to validate your assumptions before we move onto implementing the actual code fix"
- Cursor + Sonnet 3.7 + MCP feels like being in a self-driving car for the first time 😇 All that's missing is more speed + parallel agents ⚡️
- OpenAI is about to blow your mind with Active Inference... So what is it? > First introduced in the early 2000s in a series of papers by neuroscientist and theoretical neurobiologist, Karl Friston - active inference is a theory of how the brain uses statistical inference and
- Few things pretty obvious to a few AI researchers but that most don't want to believe: 1. 90% of the most impactful AI research is already on arxiv, x, or company blog posts 2. q* aka strawberry = STaR (self-taught reasoners) with dynamic self-discover + something like DSPy for
