A random mix from the whole library. Shuffle for a new set.
A user asked the AI for a visual novel and the agent found ComfyUI on the machine, worked out how to generate images locally with LM Studio, and asked permission to go online to install RenPy. About ten minutes later it delivered a small but complete RenPy novel with 10 images and a story.
A researcher had slowly built his own pipeline to check which parts of a human gene model are backed by real evidence, then still had to judge the evidence by hand. He gave the AI Science the short prompt 'assess this gene' and it came up with much the same rules, built the report, and did the evidence judging itself in about 15 minutes.
Demonstrated live: The AI searched court availability, booked the slot, and put it on the calendar without leaving the AI.
The AI with Photocraft combined people from two photos of the same location into one photo in 3 tries over 5 minutes, after the AI attempts had changed faces.
Built a discontinued-products memorial site (about 239 products) with an AI research pipeline and a human review gate, which caught an AI claim that a snack had been revived when it hadn't; two weeks post-launch Google is routing discontinuation queries to its pages.
Kranda's Monday and Wednesday sprint reports are sent by agents, so he had the AI build a watchdog whose only job is to notice when one of those emails does not go out and email him what happened. He says the watchdog exists mainly because the AI’s device permission issues make silent failures a real risk.
Noah connected Spotify to his AI and asked for a playlist built from his already-liked songs but limited to tracks he has never actually listened to, as a way to surface new music from his own taste history. The AI can also just play his liked songs on his phone or computer on request.
The AI autonomously ran Quake demo playbacks, took pixel-diff snapshots, compiled a native build and patched the game for determinism, leaving a solid regression test set.
He added an MCP server to Eagle, the Go backend for his own website. Now he can snap a photo of a cinema ticket and ask the AI to add it to his movies log on the site.
A Mac user deleted a Pages document by mistake before ever saving it, so it was not in the Trash or Time Machine. The AI searched the whole disk, including iCloud cache files, and located a copy in the CloudKit cache folder, and the document was recovered.
Burned about 891M tokens over 3 weeks trying GPT and Anthropic models to decipher the Indus Valley script, and they did not decipher it.
After surfacing the Sept 28 triple-header, Mila built a sustainable weekly rhythm around Lixka's fixed classes, clinicals, and workouts, and asked permission before creating three tracked goals: quiz prep, reflection paper, and workouts/downtime.
After putting it off for years, he worked with AI over a few sessions to build a homepage for his genealogy research. The page is up with links to eight parts of his work, and three of them already have material on them.
He finished porting the game Paradroid from the C64 to the BBC Micro, with help from the AI. Anyone can download the disk, play it in an emulator, or read through the code.
Adam Mosseri (Instagram head, 4.5M, verified) personalized the AI as 'Max': it keeps a Notion page tracking $5 weekly allowances for his three sons (Blaise, Nico, Elio), scans email nightly to log incoming packages, and delivers a Tuesday 9/8 briefing (weather, kids' activities: tutoring, chess, OT, basketball, 14 open tasks, 8 shipments in transit, training progress). Comments were dominated by anti-AI sentiment, not the functionality.
A creator who makes hundreds of NPC entries for an application, work that takes hours, handed the archiving to the AI; it archived 780 entries in two weeks.
Made an AI sysadmin bot with root SSH that runs hourly health checks, Monday 6am updates with rollback, firewall, nginx and site fixes he triggers from his phone.
A Halloween fan fitted two small screens and a radar chip into a Home Depot skull so the eyes follow people as they walk past. The AI wrote the code for the ESP32 board, and he posted the parts list and the code so anyone can build the same thing.
An LLM performance-tuned his Godot voxel game over 3 days, taking it from 12 fps to 60 fps with diagnostics and render changes.
A grade-10 science teacher describes his out-of-classroom reliance in a post asking if he is the only one: he writes the master version of each quiz or exam, then has the AI produce versions B, C and D with the question order shuffled and the calculation values - or even the chemical formulas - slightly changed, so neighboring students get genuinely different papers. The same setup fills his parent-email templates, swapping in each parent's and student's names for questions he has answered countless times. He double-checks everything before it goes out.
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.