A random mix from the whole library. Shuffle for a new set.
He built an MCP link to ESPN fantasy football and let his agents run his team in a work league: they did the drafting, check injuries and stats a few times a day, make all the moves and submit the waivers. On game days they check every 15 minutes, and after each game day a recap goes out to the league on Slack that trash talks the losers.
He told the AI to call Sarah. The AI switched to calling Gerald, a random phone number he does not know, and he stopped using Google Assistant because the AI ruined it.
He built Compressius with AI: it archives an entire website, photos and pages, into a single HTML file under 200 megabytes that can be viewed offline or printed. He built it after a friend asked why his own site export was 20 megabytes of HTML alone.
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.
The AI built a Mumble replacement in Rust from a rough spec in 2 hours; it worked flawlessly on Mac and Windows, he uses it on his LAN, and the AI built a network simulator to fix a latency issue it spotted in logs.
For years he kept a Photoshop contract just to read and write DDS texture files for his ETS2 and ATS mods. He asked the AI, and now he can convert DDS to PSD and back in batches.
Has the AI piloting his OnePlus 6T over adb, booting new candidate kernels and checking the results.
The AI got Omarchy WiFi working on his MacBook, at a cost of 6M tokens.
A Mac user was building a website with AI when the contents of his home folder were deleted over about 5 minutes. His Desktop was emptied except the active project, his Music, Movies and Pictures folders were emptied, and his keychain and SSH keys were gone. Nothing was in the Trash, and the local session transcripts were stubs, so the exact command that did it was never found.
Scheduled the AI routines leave a session behind on every run, and one routine had built up 618 open sessions that the app only lets you delete one at a time. A cleanup skill plans the job, keeping the newest sessions and any where the owner typed a reply, then has the AI delete through the app’s own session tool, 25 per call, each batch behind an approval card.
Gave AI full control to build a desktop environment he uses daily, with features appearing during the workday and lower RAM and VRAM use than standard desktops.
In a hands-on test on a $20-a-month Google AI Pro account, the AI renamed and organised a folder of 507 PDFs into 13 subfolders. The session drew a broad warning that granting folder access could include sharing the folder's contents with third parties, plus a notice that backups of connected files would be deleted after a follow-up or 24 hours.
Had an AI go through a book of 200 year old religious records and pick out references to possible ancestors.
The Nautilus file manager never offered a miller columns view. He forked it and had the AI add the feature, and the fork is publicly available.
He had given up on a years old problem getting Roon to play music on his PC. He put the problem to the AI, which read the log files, ran a test script, and fixed it in a few minutes.
The AI derives public addresses from the Xpub (no transfer access) to catch hacks or seed-phrase compromise fast.
Ahmad Alkabra posted on X that he tried an insurance prompt sourced from an AI use-case account and received safety and scope warnings, including that the AI would not pose as a licensed insurance broker. No quote, policy change, or saving was reported — the task was refused on licensing grounds.
Ran up to 50 concurrent DeepSeek subagents reverse-engineering C code from an old PC game, finding over 100 new functions for about 2 dollars.
He gave GPT a security audit skill that checks his machine against newly published vulnerabilities, patches what it can, and warns him about the rest. He runs it whenever new CVEs land, and says the patches need care because a fix can cause as much trouble as the flaw.
A blind AppleVis reviewer writes that he recorded a WhatsApp audio message from an Uber asking the AI to sign him up for an NFB CENA webinar on iOS 27 updates. The AI processed the signup flawlessly, relaying to him the survey questions the NFB form prompted for, and put the webinar on his calendar — one of dozens of conversational automations he set up in his first week.
He replaced dozens of separate the AI chats with one persistent Dot chat. Dot starts remote the AI threads on his always-on Macs to update his Obsidian vault or find order details, and it messaged him on its own about flooding in Hawaii days after he had asked about Hawaii weather.
A user who bought a paid the AI plan specifically for Dots reports its live voice mode never finishes any action: it says it is checking, then stalls indefinitely even on trivial requests like the time or weather, across Android and web. The same account's text chat completes tasks, isolating the failure to the voice-agent path.
A statistician had argued that class balancing helps mini batch gradient descent. He had the AI Astra design and run a simulation to test the claim, and the results partly corrected him: oversampling sped convergence but hurt probability accuracy, while importance weighted oversampling kept most of the speed and the accuracy. The code was cross checked with AI, and he posted the corrected conclusion as an answer.
He built Tidehook with GPT-6 Astra and generated art. Players tow salvage that changes how the boat handles, across three coastal voyages with a working crane, and the game is free to play.
He lost most of his vision this year to a rare genetic condition. With the AI’s help he built a tool that lets him play games again, designed so other people with sight loss can use it comfortably too; he plans to release it free with the source open once it is ready.
A PHP flaw finally pushed him to move an old site off WordPress. Doing it by hand would have taken all day, and the AI did the move in 10 minutes.
A self-hoster runs AI cron jobs that sweep the internet for things he cares about, check his support system for unanswered tickets, and browse X and social media to filter the valuable posts - though he admits the X timeline filtering quality is low even on a top model.
Used the AI to pull all his iCloud data into a custom web service for scanning photos and messages, then cancelled the paid iCloud subscription down to the free tier.
The AI found Instagram, LinkedIn and other apps abusing background app refresh on his iPhone. He turned it off, and his phone now ends the day at 46 percent battery instead of 9 percent.
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).
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.