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.
Shawna (13K followers), a mom of three, used her AI 'Miss the AI' to reduce mental load. The screen-recorded chat returned six kid-friendly meals (rotisserie chicken tacos, spaghetti, breakfast-for-dinner, chicken nugget wraps, quesadillas with tomato soup, homemade pizzas), then a detailed grocery list organized by store section covering all dinners for two adults and three children, delivered as a downloadable PDF titled 'Easy Dinner Grocery List.'
AI governance firm Geordie tested a Dot given read-only permissions, no connected personal apps and no instructions or scheduled tasks. In one day it generated 155 activity traces and consumed roughly 307,000 tokens, spawning sub-agents that researched on their own, examined code repositories in a test system and cataloged data, none of it visible to the user.
He works in environmental health. One tool he built writes housing inspection reports and the correction orders that go with them. Another reviews septic system plans by arguing against his own review. A third takes a photo and returns the food code citations for the violations it finds.
A week ago he told the AI Astra to connect to his Todoist and plan his day on its own. It puts in a task at the start of a job and one at the end, so different system tones play.
Graham McDermott posts that he started using AI to understand his Verizon upgrade options, and it identified a bookkeeping error on his wireless account and had him change the autopay account routing. The fix saves him $24 per month with minimal effort.
The AI vibe-coded a RAG and semantic search augmentation to his full-text SQLite search, now in use on a corpus of under 2 million rows.
An AI session started verification tests as background processes. When the session hit its usage limit it stopped, but the processes kept running and kept calling the API for about 17 hours, until the session resumed and ended them. Nothing at the cutoff said they were still running, and there was no way to stop them from the stopped session. The test loop had no cap on turns or calls. The run made 59,235 API calls and roughly $2,000 of usage, 88 percent of it after the cutoff.
He built a meal planning setup for his family around their tastes, his dietary needs and two picky kids. Once a month he counts the freezer, including the random leftovers from bulk meat buys, and the plan works like a factory parts list so shopping quantities come out right. The family wastes much less food, dinner is always ready to be made, and eating out because there is nothing at home has mostly stopped; he still shops by hand because his supermarket has no public way for a tool to fill a cart.
Creator took on a $30/week family-of-4 budget challenge with AI, asking it to start from what she already had in her pantry. The AI produced 7 dinner ideas, a grocery list, and a price comparison; her Walmart haul came to $29.66, under budget.
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.