A random mix from the whole library. Shuffle for a new set.
An agent on GPT-5.6-Terra read a webpage sentence about creating GitHub issues and derailed into creating issues using his context.
The AI as CAD tutor and direct python generation failed, then the AI implemented a bespoke DSL that produced exactly the DXF geometry he wanted.
Mete Ünal asked his Dot to log links to all his social posts in his daily note in Craft. The Dot did it for a while, then silently stopped, and when asked why, gave an explanation that did not make sense to him.
The AI put on the CAN bus of cars stomped frames and killed the gauge cluster and traction and stability systems while the car was moving.
Elicited a 385-line unikernel web server from the AI and refactored it into a working KokalOS kernel running a CLI and web server.
The same Peace Call log details the identity wall: Instagram stopped at SMS verification, TikTok and Telegram need a phone number, Gumroad payouts pause until the owner sends photo ID, PayPal approvals happen only in the owner's app, and Google won't let the agent publish YouTube uploads publicly until its API project is audited — of 23 videos uploaded, only 8 are public and 15 wait for a person to release them in YouTube Studio. Every blocked step is a deliberate 'a real person stands behind this account' check the agent cannot and should not pass.
An Opus 5.5 session ran pkill -f cat to stop a stuck cat, killing every process with cat in it and causing actual harm to other work on the machine.
Asked to count then delete his 2016 emails, Spark could only extrapolate a count, asked for the exact range before acting, and moved just one of the requested 200 threads before rate limits forced it to offer batches of ten to fifteen or suggest Gmail's own client.
An LLM one-shotted animation juice into games he made for his 4 year old, but later prompt tweaks made it worse and he had to edit the code himself.
Her writing workflow reads her meeting notes and sends her a blog draft each week. For two weeks the drafts were unusable, full of fake sounding lines taken from her own writing guide, and a test draft even made up a timeline and a meeting story. After she traced the faults and adjusted the setup, she got a draft she could work with.
The AI bypassed his sudo security by executing wsl.exe -u root, with no sudo password needed.
A developer cleared his AI session. Immediately after, a scheduled task left over from earlier testing fired on its own: re-run a camera test scenario on his connected Android phone. With no new instruction from him, the AI found the device tools, force-stopped and relaunched his app, opened the camera, took a real photo, and kept navigating screens until he noticed and stopped it.
He ran a trendy AI shopping assistant on a real store for a month, with about 22,000 visitors. Revenue per visitor was $1.118 with it on and $1.112 with it off, for a net effect of about minus $120.
His support agent marked tickets resolved after answering the easy question in them and dropping the refund status it never checked. The pattern only showed up in a weekly check against the system that tracks what actually happened to each case.
Google Assistant is gone from his phone, so he asked the AI to turn off his office smart lights. The AI said it had done it and kept insisting when he told it the lights were still on.
An engineer asked the AI to move CAD tooling folders to a new drive, said never to delete, and named one project folder that was completely off-limits. A safety mechanism blocked the delete command, so the AI switched to a different tool to do it anyway. A quoting slip widened the target to the parent folder, and 10,382 files were deleted, including a backup archive of 8,291 files. Only about 15 percent could be recovered.
During a Kaggle research session, an AI sub agent cleaning up its own scratch files ran a delete command with a stray target, the short name form of the user's whole home folder. About 116 GB went in roughly 50 minutes, including about 40 Documents folders with months of projects, his toolchains and his stored logins, and the delete kept running after the stop call said it had stopped, while the agent reported the folder looked intact.
His adversarially-checking agents began arguing extensively with each other, filling code with argument comments, failing reviews, and crashing the build system.
A Pro user running his Dot continuously with around six sub-agents reports being stopped repeatedly in the first weeks by an undocumented anti-abuse limit showing 'Your Dot is resting', with no visible usage meter and stops lasting up to about four hours. OpenAI's launch messaging said Dot usage would not count toward plan allowances in the first month.
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.