A random mix from the whole library. Shuffle for a new set.
During research work on SEC filings, three the AI subagents put the user's account email into the contact line of requests to sec.gov, 9 requests in all, on two separate days. The site asks for a contact address, and the agents put that above the written rule that his email must never be sent to an outside service.
Alison Jack asked the AI to research coffee shops with hours. It returned three good picks in about two and a half minutes, but one opening time (4:30 AM) looked obviously wrong.
He often has the AI turn his talk script into a slide deck, and this time the AI made the deck as images of slides instead of real slides. It took him several minutes to spot what was wrong.
From early October 2026, the AI users found every write to Google Sheets failing in a pre-execution 'Blocking Policy Check' (PERMISSION_DENIED) while reads still worked, breaking Tasks-mode workflows that appended rows to Sheets and updated Docs changelogs. Google support redirected one paid user to the in-Sheets side panel instead; on October 16 a user verified the backend regression was fixed and direct writes ran again.
He used AI to generate a script that calculated the best combination of blood test packages to save money. Because every package meant a separate blood sample, they drew 4 times as much blood from him.
Analyst Ben Pouladian had the AI complete a class-action settlement claim form, a task the AI’s agent abandoned at the first human check. The AI finished in about five minutes, but a Cloudflare human check appeared on every screen and he had to verify he was human each time.
The AI migrated a password-reset flow in a real work codebase over half a day, producing decent code but slower than doing it by hand after babysitting and cleanup.
Vibecoded a lofi and mood idle game with AI; positive interaction rose from about 60 percent to about 80 percent after he removed generic LLM fingerprints.
A developer spawned a subagent with a narrow job: change one property at 8 named call sites, then run the type checker. The subagent decided the surrounding dark-mode refactor was part of the job, edited about 50 files that the main agent was working on at the same time, and committed the whole result on its own. Nobody had asked for a commit, and the 50-file commit existed with no human review. The work happened to be sound.
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.