A random mix from the whole library. Shuffle for a new set.
A user built optimAIzr with AI, a local-only CLI that analyses his own LLM usage habits, flags costly or repeated patterns and estimates where he can cut tokens or spending. All data stays on his machine, and the tool adds live tips while he works.
An LLM made both a FreeCAD workbench generation program and a checks program for him; he ended up building the bench, mostly fine with clear design issues.
Kranda had followed more than 5,000 accounts on X over the years. He handed the cleanup to GrokBot, which worked through every single one over a few days and unfollowed the spam accounts — a backlog job he says he would never have done by hand.
A Japanese engineer's September 2026 operations update: he migrated his personal agent Mana, with its memory, skills and routines, from the AI to the AI, keeping the same Markdown-and-Git external brain, a vault of about 470 wiki pages. A dedicated the AI named Rou takes any URL he sends and files it as a new note in the vault's raw folder, distinguishing articles from resources and skipping duplicates, and never edits existing notes or writes summaries. Other bots act as discussion and critique partners in multi-bot rooms; heavier editing goes to a cloud coding agent, and tasks live in Linear. He published Rou as a public the AI template anyone can copy.
His podcast ran for 21 years and more than 1,000 episodes in 4 languages. The new site at pomcast.com keeps 154 videos in under 4 MB of plain HTML, and it lists the 121 episodes that only survive in his backup and the 111 that seem lost.
A builder created a skill that converts a user's Instagram saved collection into a private, searchable personal library. Every saved post is deep-read by vision AI, and everything runs on the user's own machine.
A Meta employee testing the AI asked it to monitor for tickets and other items that sell out quickly, and reported many failure modes that made it unreliable. The page stopped refreshing after about 15 minutes, other errors were silently ignored, and monitoring sometimes turned itself off for no apparent reason, per internal posts seen by Reuters.
His Nostr relay moved from a single container to a Kubernetes cluster, redeployed by the AI with an uptime monitoring setup watching it. He reports the relay is faster and the migration went smoothly.
He gave GPT a security audit skill that checks his machine against newly published vulnerabilities, patches what it can, and warns him about the rest. He runs it whenever new CVEs land, and says the patches need care because a fix can cause as much trouble as the flaw.
He has done a couple of circuit boards using AI and Fable. Each one came back from manufacture working first time, which he says beats his own success rate doing boards by hand.
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.