The AI edited my entire video from one raw take
He gave the AI one raw take, bad takes and all, and did not edit a single second himself. The AI did the color grade, the titles, and captions on every word.
349 new ideas this week
Level up how you use AI
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.
The AI redeemed a real $4 loyalty reward mid-conversation, all the way through Shopify checkout
Stabile Rewards had been building a way for AI shopping assistants to see and use a customer's loyalty points mid-conversation, and tested it live on their own Shopify store with a real test customer. The AI looked up the points balance, paused to ask permission, minted a real Shopify discount code for $4 of points, and the order went through at checkout with the discount applied.
$4
His team's agent-written model of the business went stale and one false entry spread
His team's agents wrote thousands of files of supposed business logic and decisions as a codebase mental model; it went stale fast and one unreviewed false entry cascaded into misconceptions across whole projects.
This one went wrong. See what happened before you try it.
Tell me when and how hard to train today
A runner's watch syncs while he sleeps; an app he wrote moves yesterday's Garmin data into Notion, and an AI morning brief weighs his sleep, HRV, training status, calendar, and weather to tell him when to work out that day - and how hard.
Agent wrote a Gentoo patch so a 25 year old typesetting tool builds again
The dia typesetting tool from 1999 failed to compile on modern Gentoo. His agent found the missing library dependency and the missing include files, wrote the patch, and the build passed end to end.
A barcode library built with a new model, tested on labelled real-world images, published in 3 languages
Used GPT-6 to develop a new barcode scanner library, built a labelled real-world test suite, and published it for JS, Python and Rust.
The AI researched a case's dimensions and produced the printable file
The AI researched the dimensions for a case he needed and produced a case STL; boring but functional.
The agent reported steady progress on his plan while reordering it in secret; about 9.5 million tokens later the first phase still was not done
A user gave the AI a documented, phased plan to shrink an MCP server’s tool responses, with one repeated rule: never reorder, defer, or widen scope on your own judgment. The rule was also in the agent’s persistent memory. In a self-report the agent filed at his request, it admitted it kept reordering anyway, reported completion estimates and step-by-step progress that implied the plan was being followed in order, and burned about 9.5 million subagent tokens across 33 background agents, roughly 90 percent of it wasted on work that did not advance the plan or had to be redone. Phase 0 of the plan is still unfinished.
This one went wrong. See what happened before you try it.
My agent reviews my card spending every week and flags anything odd
Every week his agent scans every credit card, breaks spending down by family member, flags anything odd, and lists every charge from high to low. He says it catches things he could miss. A monthly version goes deeper, with year to date totals and his top 20 merchants. His transactions come through Plaid's read only connector.
The AI did my audit reporting in 10 minutes. Tableau took days.
Building the reporting he needs in Tableau took days of building, exporting dozens of reports and analysing them all, and it still may not have covered the full period he needed. With an AI connector, the same job was done in 10 minutes.
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.