I built my own Lightroom style tool with AI to process my photos in batches
He generated a Lightroom style program with AI that develops his RAW photos in batches. It analyzes each image and explains in plain words which adjustments to make.
A random mix from the whole library. Shuffle for a new set.
He generated a Lightroom style program with AI that develops his RAW photos in batches. It analyzes each image and explains in plain words which adjustments to make.
The AI built a complex quiz web app for himself and friends with multiple question types, screen sync, media uploads and scoring, in about a week of evenings (build reported in-window; the comment's complaint about current models left aside).
He wanted his AI character AYN to move and talk like a VTuber. The AI drew the art, Tripo made the 3D shapes, and the AI drove Blender by script to build, fix and export the model, while he only looked at the renders and said what looked wrong. The finished model has 16 expressions and lip sync that follows the expression.
Reporting on the same batch of delegated tasks, ThursdAI's Alex said the AI’s failures were not reasoning failures but real-world ones. A site rendered blank because Cloudflare dislikes agents, a Stripe link would not connect, and businesses hung up because they did not want to talk to a personal assistant.
Uses an AI-implemented forced-alignment technique to generate sync files for epub and audiobooks, aligning a 60 hour book in 20 minutes on his GPU.
The AI tried to fuzz a Jane Street ASIC puzzle circuit, switched to a Z3 and SMT route and solved it in about 3 hours; writeup published.
A creator who fixes AI-generated images in ComfyUI had the AI build him a full desktop editor, Scumble, over five weeks starting September 4: 632 commits and about 83,000 lines of app code, tested against his own pictures. It reached 43 releases and a Microsoft Store listing, and every feature doubles as a command an agent can call.
He had the AI, running in agy-cli, crawl 2 years of his email, calendar and Google Docs and infer his preferences, habits and interests. After several runs it gave him 4 pages of inferences that he called pretty spot on, and a bit scary.
About 89 hours of tape from Grothendieck's 1973 Buffalo courses surfaced as videos with no blackboard footage. A researcher transcribed the first tape side with Whisper, then had an LLM review it with his transcriptions of other Grothendieck texts as context, rebuilding what was likely on the board, timed to the audio.
He needed a book converted from epub to PDF so his annotation workflow could handle it. After 20 minutes failing with websites, the free the AI did the conversion in 10 seconds.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.