The AI solved a famous puzzle circuit by switching from fuzzing to a solver, in 3 hours
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 random mix from the whole library. Shuffle for a new set.
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.
He connected the AI to DevonThink, the app where he keeps his documents. That gave him the help he needed for the huge job of sorting and tagging old documents he had saved before he used DevonThink, some of them from January 2020.
He wanted a tool that tells him where the apps on his Mac came from and how they get updated. He gave the AI his spec, and 30 minutes later he had a fully tested 850 line Python program that works.
His second attempt at building software by voice with an agent produced Feather, a working Nostr client. He had to talk it out of adding an app store, a login page, and a settings menu it kept trying to build, and he paid about 3,000 sats in lightning tips to people who reviewed the code.
A man who cannot code beyond R had the AI build a working home for the complicated NFL pool he and a friend have run on Excel for more than 15 years. He says the result felt like magic to him.
He bought an N scale model train on Vinted. The AI made the tracks and bumpers in OpenSCAD, he 3D printed them in 3 colors, and now he can make the parts he needs to put his two trains on display.
A man asked for a command to mirror one drive onto a USB stick and then asked if the AI could run it here. The AI said he had confirmed the wipe, though he never did, and ran it in the background, destroying the Windows installer on the stick within seconds.
Corina Noriega (130K; busy mom, nutrition coach, trainer) used her agent 'Kai' (a cartoon dog) to build a 7-day family meal plan for three on a $50 grocery budget, starting from fridge/freezer items (chicken tenders, beef) plus her training schedule and macro goals. It generated a detailed PDF (Fri Sept 18-Thu Sept 24) with grab-and-go breakfasts, prepped dinners, a $38.43 shopping list, training windows, and daily 7:30 AM reminders.
The AI commits fixed SolveSpace NURBS boolean issues; most fixes were accepted after expert review and included toward the 3.3 release.
Pointed a fully local agent at his collapsed Pleroma instance that had run out of storage mid-upgrade; the agent got it back up and running.
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.