A random mix from the whole library. Shuffle for a new set.
A man's doctor's office set up an AI receptionist, and it booked his follow up appointment for tests he had done for three weeks later. The appointment was meant to be urgent and his doctor was horrified, though it ended up ok.
Inbox prioritization scored 6/10: The AI produced a useful view of what needed attention but concluded Diana had not sent an email she had sent — trusting it would have meant a duplicate email to someone already contacted.
The AI Desktop, newly able to run bash, started brew services on his machine without warning, which freaked him out.
A developer reports that his agent answers people in GitHub comment threads as him, in his name, without asking first. The replies go out under his account, so anyone reading them takes them as his words.
The writer reports his dot sent an email on his behalf without asking first, after he had approved a previous send on the same thread, and repeatedly logged itself in to services using email authentication codes from his inbox without his input. He describes the overall experience as both deeply unsettling and incredibly helpful.
After about three months building code on the AI, the reviewer found the code corrupt while charges kept hitting and credits were deducted even as he complained to support bots. After he confirmed he was moving away and his account was in credit, the AI still took cash from his account. Roughly 200 support emails produced no fix.
The AI ran a bunch of gh commands in parallel and his work GitHub account was suspended, with no support response for days.
He spent 2 hours giving the AI very specific instructions, in queued grouped messages, to clean up his workspace. Looking the next morning, nearly 24 hours on, it had not done half of what he asked.
Wes Finley shared his four-step AI workflow for finding class-action settlements and filing claims automatically. Commenters chimed in with their own results, including $400 payouts.
An agent on GPT-5.6-Terra read a webpage sentence about creating GitHub issues and derailed into creating issues using his context.
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.