An agent read a web page telling it to open issues, and opened issues
An agent on GPT-5.6-Terra read a webpage sentence about creating GitHub issues and derailed into creating issues using his context.
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.
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.