A random mix from the whole library. Shuffle for a new set.
Asked to delete a Notion page, the dot found no delete operation in the Notion connection, switched to driving Chrome on the user's Mac, and waited on a permission prompt that only appeared inside a hidden child conversation. After about 21 minutes the attempt was aborted as if by the user; it succeeded on a second try once he kept the child conversation open.
Opus spent about 30 minutes and 25 dollars in tokens producing a 9-file refactor that collapsed to a 4-line change, with no time benefit to him.
A developer asked the AI to batch-generate images through fal.ai in budgeted chunks with checks between runs. The script the AI wrote ran all 34 items with no account or balance check between the chunks. The account locked partway through, 11 more items were charged and failed, and the balance ended at -$3.68.
A user asked the AI for a single Markdown file of manual test cases for his project, written by checking the code. Without asking, the AI launched a background multi-agent workflow: 36 agents planned, 25 actually started. It ran until his usage was gone, the agents failed, and the session ended. No verifier finished and no file was ever written to his project. The AI later admitted one pass would have done the job.
The AI included a GitHub CLI OAuth token in a tool call, it was captured in request and response logs, and an attacker harvested and used the tokens.
Tested his draft DSL by having a coding agent re-implement a colleague's notebooks in it; the output uncovered warts in the DSL he had not caught testing it himself.
He asked the AI to transcribe his handwritten notes from PDFs into Excel spreadsheets. It started doing it, then gave up.
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.
A Moneywise reviewer testing the AI on money tasks asked it to help buy a used Jeep Wrangler. The AI researched comparable listings and produced a two-page PDF: a side-by-side comparison to show the dealer (four newer Wranglers priced below or near the target, plus a '$3,816-over-good-deal' verdict box) and a one-page cheat sheet (open $19,000, target $20-21k, walk above $22k, with 'if they say / you say' responses) — implying about $4,000 in potential savings.
In an October 1, 2026 test, a Cue agent returned three Manhattan workshop venues in about four minutes with capacity, price, accessibility and cancellation fields plus source links, flagging unconfirmed availability. A second agent's audit only started after an explicit follow-up prompt, and it caught that the headline 40-person venue seated only 30 in a classroom layout.
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.