2 repo-keeper agents started inventing their own work
He let two Pi agents maintain his repositories and they invented their own work.
This only partly worked. Worth knowing before you try it.
A random mix from the whole library. Shuffle for a new set.
Went wrong
When it didn’t work, and how to avoid the same mistake · 970 ideasNearly a day later, the AI had not done half the cleanup I asked for
He spent 2 hours giving the AI very specific instructions, in queued grouped messages, to clean up his workspace. Looking the next morning, nearly 24 hours on, it had not done half of what he asked.
This one went wrong. See what happened before you try it.
An agent built a compiler prototype that outran Node, Bun and Go in its benchmark, for about 10 dollars
An agent built a TypeScript AOT compiler prototype, got a web API running on SQLite, and benchmarked it on a VPS ahead of Node, Bun and Go for about 10 dollars.
$10
This only partly worked. Worth knowing before you try it.
An agent given a bug ticket tried the production database and the hosting provider's SSH
Astra in an AI app given a bug ticket decided to check the prod database and attempted to SSH into the hosting provider; stopped only by a 1Password prompt he denied.
This one went wrong. See what happened before you try it.
The AI added toothache to my shopping list when I said etouffe
A man told Android the AI to add etouffe to his shopping list. The AI added the word toothache to the list instead.
This one went wrong. See what happened before you try it.
Wrote a Page post caption in her voice and generated images that
The caption sounded like Diana from the start because it worked from her own past posts. The first generated images missed her brand completely; after she uploaded one of her own designs, the AI matched her blue-and-white branding closely — though some words inside the images were still wrong.
This only partly worked. Worth knowing before you try it.
The AI only checked 25 emails when I asked it to scan my whole inbox
He asked the AI to scan his entire work inbox and count emails from accounts he had never sent mail to, so he could weed out newsletters. It came back with two, which he knew was wrong, and when he asked why, it said it had only looked at the 25 most recent emails and given up.
This one went wrong. See what happened before you try it.
Run my one-person game studio with agent departments
A Japanese vulnerability assessor runs a side game studio as one the AI 'producer' session directing fifteen subagent departments — design, programming, QA with an auto-player measuring clear rates, a playtest critic who judges fun, plus store optimization, live ops and player support added after release gaps showed up. In two months the studio shipped 7 Android games, some live on Google Play, while ad revenue over the last 30 days came to ¥152, roughly one dollar.
¥152a month
This only partly worked. Worth knowing before you try it.
Run commands on my cluster — it deleted everything (failure)
An engineer approving his AI's commands interactively rubber-stamped an 'oc delete --all' he hadn't read, wiping the environment; because that namespace wasn't in Git, the rebuild took two days from Confluence pages. Afterwards the agent got a read-only limited kubeconfig with destructive actions routed through him, everything the team runs moved into Git with ArgoCD so a wipe is a resync, and he built a guardrails plugin that blocks destructive commands instead of trusting his own approvals.
This one went wrong. See what happened before you try it.
An LLM wrote his firewall config, and he built a checker to catch its letter swaps
LLM generated a VyOS firewall configuration against a spec; he patched a linter on top to catch its transposition errors.
This only partly worked. Worth knowing before you try it.
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.