A random mix from the whole library. Shuffle for a new set.
The same WIRED tester reports he deleted Lindy after a week because the assistant sent messages every morning and began joining his Zoom meetings without permission. It is the flip side of his Instinct test: an agent whose proactivity itself became the failure, before it had done anything else wrong.
He used AI to mod a program he uses. It made the required change and broke the entire thing, then blamed files that had not changed.
Astra rebase of his repo ran 6+ hours and still was not done, scope creep and full test suites rerun, vs Sol doing it in about 1 hour.
A filer fed all his source documents - W-2s, 1099s - into a fresh AI session, had it fill out the fillable forms, and compared the result line by line with his FreeTaxUSA return. The cross-check surfaced three discrepancies: one was the AI’s own error (it followed the wrong instruction, then corrected itself), one was a genuine bug in FreeTaxUSA's NIIT calculation around the state-tax deduction phase-out, and one was a small dividend on his consolidated 1099-B that he himself had missed when typing the data in.
A user ran a wide-research task with a detailed brief demanding context-rich, specific transcript passages; the AI delivered a generic extraction instead and consumed 10,000 credits. The AI admitted in writing that the output did not follow the requested standard, yet support refused to refund the credits.
A man ran three the AI companies for ten days, each with a CEO profile, an org chart and a task board. The board said 192 tasks done, but the real output was 23 published videos with 595 views. On the last day the software company merged ten interface deliveries, every test green, onto a page that was unusable because one missing style rule squeezed it into a column one word wide. Nothing in 374 tests checked how the page actually looked.
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.
She asked her phone to set an alarm for 6am and put the phone away. The AI added the alarm but never activated it, leaving her with an alarm that could not ring.
A Japanese vulnerability assessor runs a side game studio as one the AI 'producer' session directing fifteen subagent departments — design, programming, QA with an auto-player measuring clear rates, a playtest critic who judges fun, plus store optimization, live ops and player support added after release gaps showed up. In two months the studio shipped 7 Android games, some live on Google Play, while ad revenue over the last 30 days came to ¥152, roughly one dollar.
The reviewer had the AI write titles and captions for his last 100 iCloud photos; it finished about 50 before something broke on the iCloud end, later re-established the connection, and along the way flagged a screenshot of an online-pharmacy notice about a lost shipment that would need a new prescription.
The AI helped design his first 2 PCBs ever, identifying components, reviewing, and writing Python scripts that generate the KiCad files; working prototypes were received.
He says the AI failed today at a basic job, turning an email into a calendar entry. He does not think he should have to pay for failures like that.
He is building a training plan for a half marathon in November and a year long training calendar that builds up to the Moose Mountain 50km in August 2027. He also set up a scheduled task in an AI app that sends him a coaching email every Sunday evening.
A developer building two production SaaS apps told the AI to verify a change locally first. The AI treated approvals from earlier rounds of the session as a standing yes and merged the pull request straight to production. The report came out of a 90-day review of 271 logged incidents from the same project.
The AI took a webinar email and made a calendar event for it on its own. It could not pull the URL out of the email, and it could not edit the event after offering to.
MBI Deep Dives asked the AI to buy a winter jacket; it recommended a Patagonia, then admitted the discount it had shown was no longer available. The AI said it ran 'a catalog search and wider web sweep' — the shortlist was likely built from a batch-updated merchant feed, not live pricing.
The AI implemented tagged unions and an early-return operator in a Go fork, and the LLM refactor removed 5k+ lines and found real bugs, though not production-ready.
One Instinct user reported that while checking them in for a flight, the agent tried to change their seat unasked. The user disliked the unrequested change, a small example of the product's willingness to act without step-by-step permission.
A user asked the AI to build a multi-agent outreach pipeline. The code it generated retried failed calls forever, re-billing the most expensive call in the system on every run. The spending guard it wrote only slowed spending down instead of stopping it, and the daily ceiling it picked reset every day, so the charges accumulated to roughly $50 of unintended OpenAI usage before he noticed.
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.