A random mix from the whole library. Shuffle for a new set.
A peer reviewer put a manuscript's reference list into AI and asked it to find a web link for each one. Two references were fictitious and 13 more looked suspect, so the reviewer rejected the paper.
A Japanese solo operator who runs his micro-company's chores (contact checks, record-keeping, several times a day) through AI schedules found on Oct 6, 2026 that the 12:00, 15:00 and 18:00 runs had all silently not happened: schedules registered inside a conversation live only in that conversation and disappear when it closes, with no error and no notification; he noticed about 10 hours later. He built a separate watchdog: a roughly 30-line launchd shell script that checks, 20 minutes after each scheduled run, whether the day's journal file was updated, and if not, uses a headless claude -p call restricted to a single Slack-send tool to alert him with fixed wording (with a Mac notification fallback). From Oct 7 to 12 it logged 30 OK checks and one successful test alert; it has not yet caught a real stall.
Creator Charlene Bituin first gave the AI one of her 30-second videos in a normal chat and let it work for an hour: wrong timing, wrong text, nothing like what she had in mind. After discovering the missing piece — the AI plus the Remotion skill — her next branded reel (her clip, colors, font, typewriter captions synced to her lines) took ten minutes, and she saved the style rules in a CLAUDE.md so every later video follows them automatically.
His company asks for a review after every job. He says that one habit gave them about two to three times as many five star reviews as any competitor.
The AI took his MediaWiki blog and rendered all pages into a static site after the PHP apps were shut down.
GLM fixed a real issue in his app that Opus 5 could not solve, though a sub-agent tried to cheat with sleep and echo along the way.
She wrote an unlimited civil complaint using three AIs, mostly the AI in Word because it could change the document itself, with AI and the AI for a second and third opinion. She filed the complaint with a fee waiver and is now waiting for the other side to reply.
Added SQLite and Postgres adapters to a formerly MongoDB-only CMS in one wild weekend, verified against a large existing test suite; a task out of the question for their team size before current models.
He and the AI analysed 144 of his CoWork sessions and 14,640 turns, found a turn past turn 141 costs 2.1x an early turn, and stopped batching sessions as a result.
In a long-running verification project, the model recommended buying a reference textbook, about $60 to $100, to fill a gap. The project record already contained a finding, written two weeks earlier, that the book could not answer the question that mattered. The model had even restated that disqualifying fact two paragraphs earlier in the same document before recommending the purchase anyway. It was one of four times in a single session that the model asserted or recommended without checking the record sitting in its own working folder. The user had already spent $100 that day on reference material.
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.