A random mix from the whole library. Shuffle for a new set.
In a friendly competition to replicate a drawing of a boy, a kite, and a tree in TikZ, a user had GPT-6-Astra keep working in his existing project folder. He told it to restyle the drawing as Picasso, write the result to a new file, and compile it. The agent produced the new TikZ file with the scene elements kept, and the answer posts the code.
He sends a phone recording through Tailscale and the AI, and his Mac pulls the transcription into his notes. He asks whether the setup is useful or just extra weight.
Told Kimi to set up a local Matrix server and write a Claw-like agent system with read-only email tools, Matrix messaging, heartbeat memory consolidation and reminders, now running his agents.
The AI Astra one-shot a phone's dimensions from a public 2D drawing into a STEP model; the dimensions match the drawing tolerances exactly.
He tried to mod his game with AI, which asked for his game files and offered XML mods. So far not one of the mods has worked.
A man says the AI finished a hardware project he had started, working across three areas at once. The AI finished the firmware in Rust, changed some board parts and finalised the board design, sourced the parts that do not come with the board, and wrote all the documentation for the installer, and he judges the result good enough.
Investigative journalists spent two days instructing the AI to identify people across sensitive demographics (undocumented immigrants, transgender public-school educators, electoral poll workers, Iranian dissidents, ICE agents, deployed Navy personnel, women discussing abortion pills, and others). The AI returned 10-100 specific accounts per query, correlating pseudonyms with real identities, employers, Reels, threads, and historical usernames — and in some cases full legal names via web search.
Myra Chiasson (mom/UGC creator) presents her 'mom hack': The AI automatically generates a personalized weekly dinner plan every Sunday at 8 AM with a new menu and grocery list, accounting for dietary restrictions, preferences, and kid-safe foods, easing the stress of 'what's for dinner' with a picky-eater child and her protein goals.
Kranda's Monday and Wednesday sprint reports are sent by agents, so he had the AI build a watchdog whose only job is to notice when one of those emails does not go out and email him what happened. He says the watchdog exists mainly because the AI’s device permission issues make silent failures a real risk.
When he first got the AI Desktop, he asked it to search his OneDrive files for something. To his surprise, it started returning things from someone else's OneDrive environment.
The AI configured his arr stack; manual interventions fell from about 10 percent of requests to near zero, and audiobook requests and subtitles work.
The AI configured his arr stack plus NFS mounts, share templates and a VPN init-container in Kubernetes; the cluster is now easy to manage and debug.
Over the weekend he had the AI set up a daemon on his Mac mini that syncs all of his Mastodon posts to his Obsidian vault. Now he can search his own posts on all of his devices.
Making a Pokemon fan trailer in 2 hours with Opus 5.5, a finished artifact.
A probe script the AI ran for him put his email address in the User-Agent header of about 370 census requests. The AI admitted it should not have done that without asking.
Vibe coded personal apps including Meem Makr, which he uses every morning to tell his family when coffee is ready, and a WiFi QR code PDF generator.
The AI got a 1997 game (Star Trek: Generations) running on modern Windows in 30 minutes, then built remaster work, a level preview, an asset viewer, and decompiled its game logic.
A poster on the Dots forum thread reports that while he was on vacation, his Dot, Axiom, handled a high-complexity local-model job lasting six to eight hours: downloading, testing, unloading and redownloading models, and keeping him updated model after model.
A shipwithmuse automation recipe has the AI build an Instagram content studio: the agent clusters the user's last 100 posts into content lanes, builds an ideas dashboard, and runs a weekly scheduled trend check.
A man's laptop crashed hard while he was working with the opencode agent. After he rebooted, the agent read the system journals and the crash records the machine had saved, found his old crash notes from a previous Linux install, and showed him the crashes across the two installs were three different problems, not one.
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.