427 new ideas this week

Level up how you use AI

Real things everyday people got it to do, and how to try them yourself.

Shuffle again

A random mix from the whole library. Shuffle for a new set.

WorkPartly worked

Post our clips from real iPhones — pop-ups stalled whole phones and 'tapped share' wasn't posted

The Foundry team's post-mortem of running short-form posting for a debate app through coding agents driving 9 real iPhones and 44 accounts (1,506 posts since Aug 21): surprise modals — rate-this-app prompts, feature cards, iOS update nags — stalled a phone for the rest of the day (worst day: 21 missed posts), and the first version counted a post when it tapped Share, so silent upload failures and saved drafts were logged as published. Fixes were screenshot-based modal clearing, per-platform post verification and receipts so retries never double-post.

This only partly worked. Worth knowing before you try it.

Design quantum circuits that beat the best published ones

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.

He built a working Nostr app by talking to his agent for 48 hours

His second attempt at building software by voice with an agent produced Feather, a working Nostr client. He had to talk it out of adding an app store, a login page, and a settings menu it kept trying to build, and he paid about 3,000 sats in lightning tips to people who reviewed the code.

WorkWent wrong

I sent an AI to hunt open source bounties for three days. It earned $0.

He gave an AI one job: earn a first real payment from an open source bounty. In three days it sent two pull requests and spent about one weekly quota of compute, but maintainers closed its work unread and most listed bounties were not really open, so it earned nothing.

This one went wrong. See what happened before you try it.

He got tired of badly formatted PDF financials, so he built a converter that turns a quarter's 25 reports into clean Excel in one batch

He is not a developer; he is a management trainee at a company made up of five entities. Every quarter, full financials go out to the management team: a batch of at least 25 PDFs from their SAGE accounting software, several of them over 20 pages long. He spent weeks reviewing test files and batches and debugging formatting mistakes to build his own converter, after finding that the AI models themselves could not do the job faithfully on larger documents: they would combine rows and categories or produce totals that added up but were not identical. The AI itself told him the task would need a hard coded deterministic app. His converter can now batch format the whole set at once, with the bolding, blank rows, sum lines and column sizing he is picky about.

WorkPartly worked

A well-meaning automation nearly corrupted a spreadsheet

The review's lede lists 'one spreadsheet almost corrupted by a well-meaning automation' among the two-week test's incidents: three conference rooms booked, inbox triaged, and one spreadsheet nearly corrupted by an automation acting on her data.

This only partly worked. Worth knowing before you try it.

Booked a Sunday 10:30 AM brunch reservation at Baltaire in Brentwood through

Seany (verified, 7.9M followers) spent a day exploring 'the coolest and most viral restaurants in LA' with his AI 'Locca' (a fox avatar). Locca suggested Baltaire in Brentwood for its viral tableside cinnamon-roll brunch; Seany booked Sunday Sep 13 at 10:30 AM through the app, visited, tried caviar for the first time, and called the cinnamon roll 'the greatest dessert I've EVER had.' Locca also picked lunch (Faregrounds, Beverly Hills) and dessert (ChocoDip LA, North Hollywood) spots he

Tell me which deal is most at risk, using Salesforce and Jira together

Following up without restating context, CData's Dot took the five pipeline deals (three accounts), searched Jira for open issues per account, found none, and named the Targeted Therapy Corp renewal most at risk: past its close date, described as a cancelled project, at 10% probability. The post says the same answer by hand can take days of asking engineering and searching two systems.

WorkWent wrong

I asked the AI to fix my phone number problem. Visible blocked it at every turn.

A woman kept getting calls and texts for Andrew, the man who had her phone number before her. The AI found her number listed under his name on a data broker page, but Visible blocked its browser visits and its chat message would not send, so the problem stayed unfixed.

This one went wrong. See what happened before you try it.

Non-coder runs her side business on 10 recurring the AI jobs, about 95 runs a week

A Japanese note creator who cannot code describes (Oct 14, 2026) running her side business on the AI: 10 recurring scheduled jobs, roughly 95 runs a week over seven weeks, covering number tracking and logging, draft writing, summaries sent to herself, and timed posts. Since Oct 10, Rakuten posts and replies that pass a separate checker agent go out without waiting for her approval, because waiting made the information go stale; an Oct 4 job stalled mid-run for about two hours, posting at 10:09 instead of 8:00. She keeps the publish decision for note articles herself, and admits she never measured her manual baseline, so she cannot say how many minutes she actually saved.

Show 10 more

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.