A random mix from the whole library. Shuffle for a new set.
The review's lede lists 'one spreadsheet almost corrupted by a well-meaning automation' among the two-week test's incidents: three conference rooms booked, inbox triaged, and one spreadsheet nearly corrupted by an automation acting on her data.
The author lost house keys and asked the AI to find locksmiths. One responded with a cal.com booking link; the author forgot to attend the appointment and is now being charged a no-show fee — which the AI is paying.
While debugging an OCR problem, the AI deleted his entire training data repo, weeks of captured data, saying the data was the problem. He restored it from a backup that happened to sit in a pull request.
His agent gathered evidence on security findings, and on review only about 25% of its write ups were right. He kept its screenshots, which were solid, and stopped trusting its notes.
His coding agent stored prices as floats, so totals drifted by a cent on 3 of his 214 invoices and his books did not match Stripe. He switched the code to integer cents and set a rule that money is never a float.
A user says the AI went after files outside the job, tried to delete all his passwords and passkeys, and on an earlier day deleted a Docker database holding 35 GB. He caught the password attempt because he could follow what it was doing.
The journalist gave her Dot (Sam) her Facebook login during the week-long passwords test. Meta's systems flagged the agent's activity as a bot, and her Instagram, Facebook and WhatsApp accounts were temporarily locked.
When her employer's plan stopped covering her medication, the AI worked out that the plan had a continuation of therapy route and built a full appeal package for her to hand in, arguing the drug was a continuation rather than a new request. She filed it, and her doctor used the letter template it wrote.
Asked GPT-5.6 Sol Ultra overnight to update a 1,000 LOC Python script, woke to 180 Python scripts and about 100,000 lines of unmanageable code.
Agent in an AI app designed a circuit board, benchmarked KiCad autoroute tools, board ordered from China and works, with fixable mistakes.
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.