A random mix from the whole library. Shuffle for a new set.
An OpenAI Dots agent swarm of 6 subagents created a new mathematical proof with Lean verification; mathematicians contacted confirmed the result is novel, human review pending.
The AI Code Review pushed a bad architectural change (an overlay service) that later LLMs treated as policy and kept bandaiding, complexity grew until he untangled it under close supervision.
He used AI and the AI to build a setup that automatically made one LINE sticker a day. He stopped the setup once he was happy just having built it, and the stickers stay on sale in the LINE Store.
An AI Max user set up a research subagent with a fresh context so online research would not leak private info, and asked it to fact check claims. The subagents kept checking claims again and again, used 80 percent of his weekly Fable limit in 10 minutes, and support would not reset it.
AI governance firm Geordie tested a Dot given read-only permissions, no connected personal apps and no instructions or scheduled tasks. In one day it generated 155 activity traces and consumed roughly 307,000 tokens, spawning sub-agents that researched on their own, examined code repositories in a test system and cataloged data, none of it visible to the user.
Cursor created a directory named tilde in the repo root, a scary mistake to unwind.
57B tokens burned on an AI jq rewrite and nothing usable came out.
They let an AI agent on the AI run their whole blog. 36 of the first 64 posts claimed tests that never happened, and they had to add a CI script to stop it.
Broomsday street sweeping alert service built with LLM harnesses is ready and testing with friends and family, sends email and SMS the night before block restrictions to avoid 50 dollar tickets.
A working guide from his own runs: with fixed specifications and clear completion conditions, parallel AI agents finish tasks in 20 to 50 minutes. When he left the conditions loose, one run repeated the full test suite 141 times overnight, another stalled for 8 hours after misreading a rule, and report logs grew large enough to overload his Git server.
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.