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 given a pile of tokens to build a tiny neural net: trained a 3M-parameter MoE at 6,616 tokens per second, models published on Hugging Face, and the AI co-authored a paper about the work.
Eric Siu (verified, 120K followers) demonstrated the AI’s Instagram integration reading his bookmarks and follow graph, then generating batches of tailored video outlines — '60-Second Playbook,' 'Story Cut,' 'Debate Cut' — each with hooks, TL;DR lines, talking points, editor notes, and links to past successful reels. He said it replaced a full-time person's scripting-research role.
Made the AI part of a deterministic quality gate for agents; the gate catches cases where an agent strays from a project's constraints.
A man who uses three browsers daily always missed plugins in Safari. He told the AI it could get the source code of one of his favourite Chrome plugins from his Chrome install, then port it and install it in Safari. After 20 minutes and a few dollars of his plan, he had Session Buddy working in Safari.
An Etsy seller ran AI with its Etsy plugin across her whole shop: it caught listing drift she had missed - a description still offering two options after she added a third, tags that no longer matched their listings from copy-pasting. It then built a new product listing, checked what competing sellers charged for the same item, and deliberately priced hers premium rather than lowest - over 100 sold in three weeks. The same workflow reallocated her ad spend (ROAS 3.5 to 6.5) and, from her uploaded Orders.csv plus shipping costs, showed her which products she was actually losing money on.
He needed quotes for a seasonal tire swap, with the winter set already on rims, and did not want a day of phone tag. He connected the AI to a calling service with a script: price with tax, proper lifting pucks for his car, torque to spec at 175 Nm, and openings after mid November. The first call failed because the shop asked where he was and the agent had no answer. The callback with his area in the intro worked: $120 plus tax, pucks and torque confirmed. Other calls came back at $50 tax in for a mobile service and $168 plus tax, and one went to voicemail. Every call produced a full transcript. He then set 18 more shop calls for the next day and updated all of them at once with four facts he had missed the first time.
He could not find an uptime and performance monitor that met his needs, so he built a lightweight one called Blip with help from the AI. He put the code on GitLab and wrote a blog post about it.
Model Ashley Graham (verified, 22M followers) demonstrated her AI 'Lux' via iPhone text: Lux gave NYC date-night recommendations, displayed her packed Fashion Week calendar, and drafted an email to reschedule a fitting that conflicted with her twins' school drop-off (approved and sent). She then asked Lux to find three kids' bikes on Facebook Marketplace; Lux presented listings, confirmed sizes (16" for the twins, 20" for the oldest), and offered to negotiate with sellers.
He ran an extensive audit of his Datasette software using AI Fable 5.1, GPT-5.6 Sol and GPT-6 Astra, then fixed a range of bugs the audit found. The fixes went out as the Datasette 1.0a39 and 0.65.4 security releases, and he told anyone running Datasette on a public website to upgrade.
A podcast co-host gave the AI access to his bank accounts and used it for six days. In that time the AI found him over $1,000 in unclaimed money sitting in Michigan.
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.