Thiago Ricieri 🥭

AI-powered automated marketing screenshot tool for SwiftUI github.com/ParthJadhav/io…

So your app got copied. What next? With AI and vibe coding, functional clones of any app be generated in days. But just because someone can duplicate the app's features, doesn't mean you can't defend your hard work 🤺 TL;DR on our developer's guide to copycat apps 🧵👇

Why does superwall keep failing now at validating the paywall for a product subscription that is already imported and live?

Every button needs these 5 interaction states @AdhamDannaway

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

UI/UX Designers, here are my go-to best design resource sites on the internet you should bookmark: Design Library → curations.supply Landing Pages → landing.love Saas Websites → saaspo.com AI Mobile App Builder → sleek.design/?ref=abrahambw Fonts → uncut.wtf Animation → 60fps.design Mobile Apps → mobbin.com/?via=abraham Brands → rebrand.gallery Icons → hugeicons.com/?via=Abraham Design Systems → component.gallery

Even though you don’t want to, it’s not fair, and you have no idea what you’re doing, you just have to do it. It takes what it takes.

AI LLM model brand SVG icon collection github.com/lobehub/lobe-i…

if you are in saas, pivot to service service as a software report -> action people want things to be solved not just reported

This is a free list of prompts for your keyword research!

You want to kill distraction? Give yourself a worthy goal. Your brain will fight you until you point it at a real mission.

Browser extension converts web pages to Markdown for LLMs github.com/Ademking/MD-Th…

AI-powered Instagram carousel designer using Claude github.com/Hainrixz/open-…

Meet tiktok_energy, the open-source AI model that's bringing viral content magic to developers. This Apache 2.0 licensed model captures the essence of trending video energy, letting you analyze or generate content with that signature platform vibe. It's a fresh tool for creators and builders.

Open-source AI agent for Meta Ads management github.com/TheMattBerman/…

Instead of watching Netflix tonight, watch this 2-hour Stanford lecture. You’ll learn more about how ChatGPT, Claude, and other LLMs are built than most people at top AI companies learn in years.

Do the opposite of the average person, and you'll be successful: Stop following rage-baiters. Don't get mixed up in politics. Be kind to everyone. Be optimistic. Do insanely good work always. Eat well, sleep well, and train hard. Great lives are remarkably simple.