A home-lab owner reported on X (via WhatAgentsCanDo, Oct 19) that, still in bed, he sent the AI a link to a post containing a setup recipe for a new DeepSeek model (DeepSeek-V4.1-Flash-1017, EXL3) across two NVIDIA DGX Spark machines and asked it to do the setup. The AI was not installed on the Sparks, but they shared a network with its computer, and everything was ready to test by the time he got up; he says he does not know exactly how the bot reached the machines.
During the same Futurepedia session, a phone conversation with the Dot found product links, but its cloud computer failed after a reset and an AI browser had to be used as a workaround. The scheduled-task tab also would not open during the recording.
This one went wrong. See what happened before you try it.
Engadget reporter Karissa Bell tested the AI for a few days starting with her Meta-app activity, since she was initially cautious about granting access. Alongside the recipe book, she had her agent ('boo') compile the restaurant posts she'd saved on Facebook and Instagram into a searchable guide organized by city — turning a dead-end save pile into a usable dining shortlist.
He finished setting up Obsidian so new notes file themselves into the day's folder and link into daily, weekly, monthly, quarterly and yearly notes. The templates behind it were made by the AI, and he says it would have been impossible without it.
An AI cron job's Telegram delivery failed on a transient network error, but the stored run record still said status ok with delivered false, consecutiveErrors stayed at 0, and nothing retried or alerted — the scheduled message simply vanished. The failure was only visible by digging into the run diagnostics; anyone watching the chat or the job's status saw a healthy run.
This one went wrong. See what happened before you try it.
He is a photographer who found typing alt text for every photo slow going. He built a small agent on his own n8n server: he sends a photo through an Apple shortcut, the agent reads the picture with a local Qwen model, adds the camera data, and saves the finished alt text in an Obsidian note, ten photos at a time.
Cornell's third live demo on How I AI: The AI converted his 20-year-old blog into a daily podcast, an archive-repurposing use case for a long-running content creator.
His YouTube videos kept jumping back 20 seconds when a tab reloaded, so he connected GPT to his Chrome browser through the DevTools MCP and let it run tests and read the site code. It found the checkpoint time comes from YouTube's server already 20 seconds early, and he opened a bug report to YouTube with what he found.
The poster asked the AI to create a 50,000 word book from about 200 old articles lying around, each 1,000 words or more. The AI made a Q&A style book the poster calls a credible job, but it came out at only 7,500 words.
This only partly worked. Worth knowing before you try it.
He built a VRChat world with GPT-6 Astra and published it. The world is a high rise lounge based on Roppongi, with night views, space to chat, and a game to play.
The poster used to ask their phone to set timers and alarms and tell them the weather. Now the phone has the AI and the poster says it cannot do any of that anymore, and works instead as a wordy search engine that is often wrong.
This one went wrong. See what happened before you try it.
Adam Mosseri (Instagram head, 4.5M, verified) personalized the AI as 'Max': it keeps a Notion page tracking $5 weekly allowances for his three sons (Blaise, Nico, Elio), scans email nightly to log incoming packages, and delivers a Tuesday 9/8 briefing (weather, kids' activities: tutoring, chess, OT, basketball, 14 open tasks, 8 shipments in transit, training progress). Comments were dominated by anti-AI sentiment, not the functionality.
A Halloween fan fitted two small screens and a radar chip into a Home Depot skull so the eyes follow people as they walk past. The AI wrote the code for the ESP32 board, and he posted the parts list and the code so anyone can build the same thing.
He pointed the AI at a downloads folder with over 1,000 media files and at his Jellyfin library. The AI made a queue file he could import into HandBrake, and he says it saved him a lot of time.