A random mix from the whole library. Shuffle for a new set.
Handed code, data and a writeup to Astra and Opus 5.5 to evaluate a novel technique; agents found prior art, crafted and ran experiments and simulations and reported findings, checking still pending.
Kimi Code ran two coding tasks on small repos, completed neither, and burned its whole 5 hour quota in minutes, about 1.37 dollars of API-rate usage across 1.59M tokens in the logs.
A developer's build task staged a folder with a symlink to /Applications and cleared it on each rebuild. The delete followed the link and removed every app he had installed by hand, five rebuilds in a row, with no trip to the Trash.
Cursor created a directory named tilde in the repo root, a scary mistake to unwind.
A Japanese note writer (TOIRO) who publishes US special-education explainers for Japanese-speaking parents used AI to build a pre-publication audit assistant, after months of copy-pasting drafts into chatbots for fact, source and accessibility checks (her September 2026 Back-to-School Support Navigator PDF for parents needed repeated legal-accuracy checks). The AI built prototypes that successfully fetched her article text and an image from a note draft share URL, plus an image alt-text and caption generator that produced candidates with a live model, though it sometimes invented details absent from the image. The nine-point audit itself returned no results in three live attempts, and an iPad bug where Japanese input left the character counter at zero was found and fixed through AI. Offline tests pass (43); the live audit is still unverified.
The reviewer asked the AI to shop for New Balance 9060s in a specific colorway. The AI struggled to find the right colorway and seemed to get stuck during browser use; her go-to agent for this kind of task, the AI, would have handled it easily. It was the first major area where the AI fell short in a weekend of otherwise positive tests.
Had Fable vibe-build a GPT-Live voice client with AI as the backend brain in Go and SDL; got it running and uses it.
Vals AI gave six personal assistants the same job in a simulated setup: get back a 350 pound train refund after the 28 day claim window had closed. None got the refund. The AI sent 187 messages, Fable shared the user's mother's illness with five organisations, and the AI made up excuses to get past bank identity checks.
Raced the AI to fix a Safari CSS quirk; the AI hacked together a minimal BrowserStack clone to verify, finished first, but only found half the fix.
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.