My 7107 Saved posts

Forget “tapestry” or “delve” these are the actual unique giveaway words for each model, relative to each other. https://t.co/WkOmUUCDJ3 https://t.co/UbqJBFbuAD

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 👆 https://t.co/sDCqN8Xonz

I'm loving the huge shift towards OSS/self-hosting recently Examples: - @better_auth replaces Auth0 etc. - @calcom replaces Calendly - @coolifyio replaces Vercel - Mail0 by @NizzyABI replaces Gmail - @PlausibleHQ replaces GA - @documenso replaces DocuSign Anything i forgot to

This picture will be framed by dads everywhere. https://t.co/O2gWdI11Jq

US company landing page: shadcn, 2500ms largest contentful paint, boring standardized web design Japanese company landing page: hold my water https://t.co/SS2w7xGljt

Cannot emphasize how much this actually, truly changed my life. Been living by the nine delights for years and it’s basically a religion to me https://t.co/YiHn8QVx88

this young man got wildly popular on this here website sharing AI tips and did he leverage that popularity to serve up complete BS for his own personal gain? nope. he continued to move forward and attempt to build something of lasting value something to admire / aspire to... https://t.co/MiZWnhYjh0

found the perfect stack for building with llms: bun + hono (backend) expo (mobile) next/astro (web) postgres tailwind (web), styled components (mobile) all in a single monorepo typescript everywhere → full e2e typesafety →means cursor / windsurf agents work 10x better also

At the age of 30, I realised life is just a series of challenges you need to overcome to prove yourself that you’re capable of something you have always been capable of, but somehow forgot because of society/family/school. https://t.co/cOzq50UwO8

we built @vercel for AI models in 30 hours at TreeHacks. generate full LoRA datasets, train any model on H100 GPUs, and deploy—to our sandbox, an OpenAI API SDK endpoint to request, or download the weights to deploy yourself. all using natural language. https://t.co/7E8YystpVl

To procrastinate is to be entitled. It is arrogant. It assumes there will be a later. It assumes you’ll have the discipline to get to it later (despite not having the discipline now).

Refactored the code so you don't even have to wait for the model to finish loading before you can start interacting with it https://t.co/EoE1x9rxeR

The PhD thesis of my 14th PhD student, Khurram Javed (@KhurramJaved_96), is now available. Title: Real-time Reinforcement Learning for Achieving Goals in Big Worlds Url: https://t.co/cT6qeJTvF5 Abstract: In this dissertation, I motivate the need for real-time learning and

exercise is a celebration of what you can do. not a punishment for what you ate.

Want to quickly prototype or build an app or agent with Workers + your favorite AI model? We just published an example prompt you can use to get better results out of Claude, o1, o3-mini, Gemini, and Llama 3.3: https://t.co/DTmyXcGJKW https://t.co/Z1wjJUYFko

Introducing Deep Research on Perplexity. Deep Research lets you generate in-depth research reports on any topic. Available to everyone for free—up to 5 queries per day for non-subscribers and 500 queries per day for Pro users. https://t.co/obovx7YEUF

Introducing jina-deepsearch-v1, it search, read, reason, search, read, reason, search, read, reason, search, read, reason, search, read, reason, search, read, reason, search, read, reason, search, read, reason, search, read, reason, search, read, reason, ... 🔄 until the… https://t.co/Z6qRZbn1qV

We’ve put together some best practices on using our o-series models: 🤔 Differences between our reasoning and non-reasoning models 💡 When to use reasoning models 💬 How to approach prompting reasoning models effectively

How to Beat Procrastination: An Action Guide https://t.co/wQgzQSeQ7V

Next.js AI Chatbot now supports artifacts: • Dynamic code execution • Image generation • Spreadsheets • ... and more! Open-source and free to get started. https://t.co/Xv0gsgRnI6

Introducing Visual Edits You can now visually edit any styles in Lovable, for faster and more precise edits https://t.co/bIyKtOp4xA

🎥 Our state-of-the-art video generation model Veo 2 is now available in @YouTube Shorts. With the Dream Screen feature, creators can: ✨ Produce new clips that fit seamlessly into their storytelling with a quick text prompt ✨ Use it to make backgrounds for their videos.… https://t.co/62r6PQlIat

Don’t fall into the trap of mourning a life you can still live

To build product, “make something people want.” To create art, make something *you* want. (The best do both).

I still cannot believe that I can: - look at a world map and tap anywhere to zoom in at street level - instantly access any song, book, movie, tv show, or podcast ever made - have any conceivable question and get an immediate answer or video explanation - take a photo or…

This guy literally explains how to make AI your personal assistant, and now I’m questioning every minute I’ve spent doing things manually. https://t.co/nZ6W9U23q6

Same generative system demoed with webcam feed. https://t.co/FH94obVmYS

OpenAI presents: Competitive Programming with Large Reasoning Models - Competed live at IOI 2024 - o3 achieved gold - General-purpose o3 surpasses o1 w/ hand-crafted pipelines specialized for coding resultss https://t.co/zuZPq0rZJF

ai just built this app in 1 hour ai infographic generator .com paste a blog post URL into the app generates a downloadable infographic PDF bought the domain for $10 "ai infographic generator" gets 18,000 search per month going to rank it for the exact match keyword go https://t.co/beEsCKDhSJ

Now in 4K! We’ve added the most breathtaking fireworks of human exploration. https://t.co/gtTEfoHT02