My 1083 Bookmarks & Retweets

2020, running out of money, solo founder, HQ in my makeshift bathroom office. little did I know Polymarket was going to change the world. https://t.co/TktiCXQgXr

Here's a cool prompt for anyone using Cursor to learn coding. I believe the best way to get better at coding in 2024 is to just make AI guide you step-by-step though your project and read the documentation. Paste in Settings > Rules For AI 👇 `# AI Code Tutor — You are an https://t.co/QVOLNEhUTd

3DTopia AI: This text-to-3D model can create an entire film scene in just minutes! 3D AI is progressing faster than ever! I truly believe AI Powered 3D will become the ultimate tool for AI filmmaking. We’ll finally have full creative controls without consistency issues. We’re https://t.co/uam6s2kkwV

Just spoke to a founder who could pay zero taxes on more than $400M when they sell their company It's completely insane tax jiu-jitsu yet fully legal with how the law is written Here's how they set it up:

Guys omnigen is pretty cool This is literally the future of media generation https://t.co/vYbd7WQorr We need to build this more of this dataset asap ASAP!!! https://t.co/mJ1jKyh8YA

It's done! I read 3,000 startup pitch decks. I wanted to find what the incredible pitches had in common. Was there a "secret ingredient" unifying them? YES. The 4 best (that VCs wanted intros to) had the same talking point:

The AI tool stack we use to build Jam: In-product API: @GeminiApp, @OpenAI Prototyping: @heyglif Code: @GitHubCopilot Prompt eng: @promptfoo Podcast production: @wondercraft_ai Clips: @OpusClip Meetings: @GrainHQ PRD: @chatprd Writing: @perplexity_ai, @AnthropicAI, @OpenAI

1/n The Renaissance Mind: How to Be a Scientific Polymath in a Specialized World Modern science, much like the music in…

1/n The Renaissance Mind: How to Be a Scientific Polymath in a Specialized World Modern science, much like the music industry, thrives on categorization. Scientists, like musicians, often operate within well-defined genres – disciplines and subfields – that dictate the https://t.co/XRpl8jooiq

I took Arvid's post as a personal Sunday hackathon challenge and built an open-source AI investigator! He asked about frameworks for running AI agents to scrape URLs and "do some data extraction until they find a certain kind of information" - like an AI investigator. 💡 The

The cheapest serverless stack for MVPs: Clerk Auth: → Free to 10,000 monthly active users Convex Backend: → 20 free projects (Supabase only has 2) → 0,5 GB Storage → 1 Mil. function calls Vercel Hosting: → 200 free projects → 100 free daily deploys Missing anything?

Build a multi-agent AI news assistant using OpenAI Swarm and Llama 3.2 running locally on your computer (100% free):

This is how I use LLM to scrape 99% of websites Many people didn't realise you can build agentic scraper to: 1. Handle Authentication, Human verification, Captcha 2. Handle pagination & complex UI interactions 3. Adaptive as website structure change 4. Scrape large set of data https://t.co/wLlGdCMq0Q

curl https://t.co/52oLHl30I3 This is our Meta-Prompt. It allows LLMs to understand our Reader, Embeddings, Reranker, and Classifier APIs for improved codegen. Using the meta-prompt is straightforward. Just copy the prompt into your preferred LLM interface like ChatGPT, Claude, or https://t.co/5WF4hRjEwS

Free scientific illustrations for biologists! 😍 @NIH has released a library of 500+ free scientific illustrations to create figures, presentations, and illustrations! all freely available in the public domain. Retweet and spread the message! https://t.co/p1bD1kxO7H https://t.co/kglaHfLb73

Wow! Meta dropped an open NotebookLM recipe: NotebookLlama 🔥 It uses L3.2 1B/ 3B for pre-processing the PDF, L3.1 70B for Transcript creation, L3.1 8B for re-writes and Parler TTS for Text to Speech ⚡ Step 1: Pre-process PDF: Use Llama-3.2-1B-Instruct to pre-process the PDF https://t.co/L7hb5GsMtl

As a startup founder, if you never want to run out of cash, save these 8 lead generation pillars and 24 tools 🦄 https://t.co/mKw1R2FatL

All rejected papers share one common flaw: a weak discussion section. I know because I used to write them too. If you're stuck on the discussion section, wondering how to tie it all together, this is for you: https://t.co/OIKrZUI6o9

🔹STORM🔹 Stanford University’s free, public app automates comprehensive research and report generation using AI to create Wikipedia-style articles with citations from web sources. STORM is incredible. I asked it to write a research paper about the use of AI in DNA analysis https://t.co/EK0ms1Xb1L

Microsoft released a groundbreaking model that can be used for web automation, with MIT license 🔥👏 OmniParser is a state-of-the-art UI parsing/understanding model that outperforms GPT4V in parsing. 👏 https://t.co/BqQ1pkCs8T

For new PhD students in social science (and some old professors - I sure needed this a few years ago!): prepared some notes on what the "2024 PhD Tech Stack" should look like. Goal: your research is replicable, accessible, and efficient. 1/9

After: 12 years 50k+ companies using our products $200M+ exit I left Paddle and the subscription economy. Here’s why 👇 https://t.co/aawZvGKGUZ

students have finished their 5-wk midterm projects, which they had to test with at least 100 people 1. shipping code for real users, and iterating, led to different statements than i usually hear from design students imo these are the right priorities https://t.co/WM6Bg2nood https://t.co/OWhrnA4hB6

So @readwise dropped a 1 click integration to NotebookLM - allowing me to search every highlight in every article I've read in the last 6 years and every kindle highlight for the last 12 years, in my own language, with citations. Oh and it auto updates with each new highlight :) https://t.co/8X8O3V8SZX

Introducing NextMaster An open-source ecommerce @nextjs template inspired by McMaster-Carr, optimized for performance with over 1 million products. A thread on how I built this with @rhyssullivan and @ksw_arman 🧵 (video is not sped up) https://t.co/2UYA03kOfW

I follow a very simple heuristic whenever I try to understand a concept, it's not original in any way, I borrowed this from a 3b1b video. I ask the following questions: - What is it saying? - Why is it true? - When is it useful? It works really well

"Chief Automation Officer" - A scrappy semi-technical generalist they've been 10x'd with LLMs, cursor, zapier ai, etc. @stephsmithio called it out back in '23 who's doing this as a service? https://t.co/m5D6cZs1dC

WOW. @Microsoft just open-sourced the code for one of "THE MOST" influential Paper of 2024 🔥 1-bit LLMs (e.g., BitNet b1.58). Now you can run a 100B param models on local devices quantized with BitNet b1.58 on single CPU at 5-7 tokens/sec 🤯 The dream we have all been waiting https://t.co/dxwZPewfvb

was left so inspired by this tweet that i made a video about it https://t.co/QWFvl4EIjj

One of my best procrastination hacks is I will procrastinate on one thing but do something else that'll be also quite useful Like now I should be working on Hotel List but instead I am improving Photo AI's videos so they can speak Then I go in circles from project to project