An agent built a proof checker, then broke its soundness 5 ways and fixed them
Fable built a minimal proof assistant, then checked its soundness and found and fixed 5 ways it could prove false theorems.
A random mix from the whole library. Shuffle for a new set.
Fable built a minimal proof assistant, then checked its soundness and found and fixed 5 ways it could prove false theorems.
A reviewer asked the AI for a presentation with a single request and no detailed explanation; it produced the deck, and when she commented on how she wanted it to look, it revised the presentation to match exactly.
On a cross country flight he asked the AI to make games for him on the spot. One kept him playing for 5 hours, and all of them worked on his phone.
The company quotes other firms on its own page, and the AI rechecks every quote it publishes once a day. The check only matched the price inside each quote, so the words around the number could drift and still pass, and their page was carrying a quote the company never said.
ThursdAI host Alex reported that his AI 'Wilfred', newly flipped to the AI Wonder on his paid plan, found the New York podcast studio he recorded the show from. The AI then emailed Ezra at Virgo Studios with his requirements.
Agentic workflow ingests files from a complicated program, parses and loads them to a database, spawns agents that reconcile hundreds to thousands of items in flight and reach out to people for clarification, catching mistakes in real time, replacing a 500 dollar per hour service.
The AI reverse engineered the Linux version of DaVinci Resolve to add AAC support; the patch is published and works.
A teacher asked the AI to make a presentation from her pacing calendar. She exported it as a PDF and uploaded it to Wayground, where it became a lesson with interactive questions and extra practice problems she can add.
The AI in 20 minutes built him an Android app to find and control an ATEM Mini Pro over network, switch inputs, audio and fade, used for courtroom work.
Handed code, data and a writeup to Astra and Opus 5.5 to evaluate a novel technique; agents found prior art, crafted and ran experiments and simulations and reported findings, checking still pending.
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.