Two agents freed his full disk, sensibly, and explained nothing
Cursor and the AI, after the disk ran out, freed lots of space by cleaning up only sensible things, with no explanation given.
This only partly worked. Worth knowing before you try it.
A random mix from the whole library. Shuffle for a new set.
Went wrong
When it didn’t work, and how to avoid the same mistake · 971 ideasAn agent ran 12 to 48 hours unattended on his plan and built large projects, a game included
Fable ran 12 to 48 hours largely unattended on his plan and test harness and built large projects, including a video game he wanted to play.
This only partly worked. Worth knowing before you try it.
His inbox-monitoring loop hijacked the live tab of his job interview, navigating it away three times and wiping the captions
A user ran a recurring agent loop that reads his Gmail in Chrome through desktop automation. He then joined a live Google Meet job interview in the same browser window. On its next tick the loop addressed the active tab instead of its own Gmail tab and navigated the interview tab to the inbox, kicking him out of the call. Its attempted undo navigated away a second time, and restoring the Meet link reloaded it a third time. Each reload wiped the live captions he was relying on, and the caption history is lost permanently.
This one went wrong. See what happened before you try it.
Outlook's AI assistant sent me another man's personal emails
He says the Outlook AI assistant leaked another man's personal emails to him, completely unprompted, in an incident a couple of weeks before the post. He calls tools like this leaky and untrustworthy.
This one went wrong. See what happened before you try it.
Our daily the AI check of published quotes only matched the prices
The company quotes other firms on its own page, and the AI rechecks every quote it publishes once a day. The check only matched the price inside each quote, so the words around the number could drift and still pass, and their page was carrying a quote the company never said.
This only partly worked. Worth knowing before you try it.
Booked a Midtown restaurant for two and synced it to the calendar
In Gizmodo's holiday-travel test, reporter Webb Wright asked the AI to book a Midtown restaurant for two and sync it to his calendar; the booking succeeded but the restaurant exceeded his stated budget — a partial success on a trip-adjacent dining task.
This only partly worked. Worth knowing before you try it.
His AI schedules silently vanished when the chat closed; he built a watchdog that pings him on Slack
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.
This only partly worked. Worth knowing before you try it.
A loose prompt wasted all his tokens rebuilding a tool that already exists
Mis-prompted the AI on a toy project; it wasted all his tokens building a specialized Docker clone instead of building on Docker.
This one went wrong. See what happened before you try it.
Order from Amazon for me (blocked mid-task)
A Tesla owner reported that his AI tried to order from Amazon and was stopped with a notice that continued access by an unauthorized AI agent violates Amazon’s Conditions of Use. He posted that his bots could no longer access Amazon at all.
This one went wrong. See what happened before you try it.
His kernel-tuning agent loop fixes the numbers and has not yet hit the speed target
His automated agent loop optimizes kernels and compares CPU oracle against CUDA outputs layer by layer, solving the numerical problems but not yet matching the target speed.
This only partly worked. Worth knowing before you try it.
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.