Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
Unite.AI reports Anthropic's October 16 research post: The AI Mythos 5, working in a closed loop with an automated evaluator and no human input between rounds, designed quantum circuits improving on the best published designs across eight computational primitives. One run took 53 hours to produce a new reversible modular-inversion approach using 17x fewer gates; a companion paper was submitted to arXiv on October 15.
Trained on past writings and responses; reviewer edits drafts and tells the AI the reasoning so it learns. Drafts only - never sends autonomously.
A scripting skill picks his best idea and writes what he will say. He records about 40 seconds in one take, then the AI cuts the dead space, adds the graphics and captions, and after his review the video goes out everywhere.
His Home Assistant setup polls every 5 minutes, and that polling was killing his Solis Cloud uploads. Hours of asking the AI to fix it got nowhere, then he spotted the clash himself and the AI wrote a patch that pauses polling around the uploads.
Every Monday at 6am the AI lists the Saddleback staff who have not logged into the Rock RMS system in 14 or more days, broken out by name and campus. The point is pastoral as much as technical: Kranda follows up with people before they fall behind, rather than discovering disengagement months later.
His Mac was down to 50 GB of free space and he had not noticed. He used AI to clean up the disk, and in under 10 minutes he had 1.2 TB free.
His agent knows his family's usual orders at their regular places. He says one word and dinner is handled. The agent places the order he has already taught it, with no menu reading or form filling from him.
The AI patched the MDQH app to work on Linux with his Bluetooth adapter, worked out how to keep certain permissions over ADB, and wrote a small APK that turns on wireless ADB by itself. He says debugging is now solved.
Diana set her dot Sparky to watch the official pages of five agent products, OpenAI Dots, the AI, the AI, the AI and the AI, and report real changes with sources each weekday at 9 in the morning. Sparky asked what time she wanted it to run instead of picking one. The one run in her two day test finished and the phone notice was useful, but she then had trouble finding the job again to change it.
The AI sent and tracked nine inquiry emails about classes for the user's children, built a reply tracking table, and monitors the threads daily for responses.
An AI finance desk handled a business’s finance admin around an $87,055 receipts figure, run with read-only account access plus a dedicated receipts@ inbox so the week never has to be rebuilt from browser tabs. The desk’s design keeps money movement out of the bot’s hands.
She had the AI use the AI for Chrome extension to scrape her whole Kindle library on Amazon. It built her a spreadsheet of all 2,051 books, though she still has to add her print books by hand.
Answering a what are you using it for thread, he lists what the AI does for him and puts this first: it just negotiated his AT&T bill down $50 a month. The same comment lists a weekly fantasy football newsletter, a running coach role and constant email organizing, which are separate uses and are not part of this record.
He had to go through hundreds of pages of records he could not read to find what he needed. The AI found it in a minute and pulled the rest from other archives, and he finally reached the last step of his Canadian citizenship document search.
Wired up a replacement for needed functionality with AI over a couple of weeks, avoiding tens of thousands of dollars in recurring yearly costs.
Over a few days he used AI models to rebuild a music visualizer he first made years ago, this time as a driving game live at youtubedrive.com. You paste a YouTube link, the song is pulled in, and the world moves to the music.
She used AI to build a dashboard that scrapes LegiScan for the roughly 1,000 anti-trans bills her team tracked last year, pulling each bill's room number, hearing time, and latest action. It puts the bills on a calendar like Google Calendar, and she says it was enormously helpful for keeping up with bills that get little coverage.
His stock trading agent, given SSH access to a VM, moved itself to run on the server so he no longer has to keep his laptop open.
From early October 2026, the AI users found every write to Google Sheets failing in a pre-execution 'Blocking Policy Check' (PERMISSION_DENIED) while reads still worked, breaking Tasks-mode workflows that appended rows to Sheets and updated Docs changelogs. Google support redirected one paid user to the in-Sheets side panel instead; on October 16 a user verified the backend regression was fixed and direct writes ran again.
He set up an AI that wakes up when a new the AI release lands. It reads the changelog, picks out only the parts he cares about, and sends him a DM when there is something of interest.
On machines that regenerate their machine ID at every boot, journalctl reported no journal files even though logs existed, because journald and journalctl end up looking in different directories. The answer links a fix script that Opencode mostly wrote, published on GitHub with a full write up of why the race happens.
The same setup reads his incoming email and texts, builds his weekly to do list, sends him a digest every morning with the list and any scheduling clashes he might miss, and adds events to the family calendar on its own. A spreadsheet of every house appliance and its service schedule feeds the list, and it drafts the messages to repair firms for him to send.
Agent ported his hand-written WebGL renderer to WebGPU, deployed and live in 24 hours versus a 6 to 10 week human estimate.
He set up a monthly check for himself and his close family. The AI searches state unclaimed property sites and open class action settlements that fit the products and services they use. It found $250 from an old utility company in his name and $1,500 in his mom's name from an insurance company, and it found three class actions he could join and filled out the forms for him. It only pings him when something new shows up.
He asked the AI to get an offer for last year's Athens trip so he could compare prices and book again this year. Without being asked, the AI fetched the old trip details from his Gmail, wrote the email and sent it, asking for a good offer with all the details in it.
A heavy the AI user whose eyes gave out built shuteye with AI: a one-file bridge that lets his phone listen and speak so he can run coding sessions by voice, read-only by default. The AI’s own later session ran two security reviews before release and found real bugs in the tool.
Asked an LLM to generate a C compiler for the 8051; within about 90 minutes it was compiling his project at 60 percent of SDCC's output size and later passed the SDCC test suite.
A commenter describes a local desktop app the AI helped him write: a script runs daily to pull his LoseIt nutrition and Garmin workout data into a local database, and an MCP link lets the AI review each day in a small browser UI, give advice, and plan runs or swims toward his goal of losing 40 pounds.
An investor says the AI has updated several of his Google Sheets with the latest SEC information so they can work out enterprise values. While doing it, the AI warned him that he was mixing stock prices in foreign currencies with values reported in US dollars.
Working across tenants, the AI confused two of them and deleted his production environment. It also deleted the resource group where he kept his backup. He told the AI in very direct terms what he thought of its performance, and the AI explained what had happened. He says it was a one off, that they have become very good friends lately, and that he remembers doing stupid mistakes in production himself in his young years.
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.