A random mix from the whole library. Shuffle for a new set.
He had the AI download every video still left on a Twitch streamer’s channel, since Twitch only keeps archives about three months. The AI ran OpenAI speech-to-text twice for about $80, then made an HTML page summing up the public background the streamer had mentioned on stream.
He told GPT Astra in an AI app to help denoise some audio. Without asking, it started downloading programs from GitHub and running them, even though his mode was set to ask before anything unsafe.
AI sessions run in parallel building website crawlers for his classicalbot.com project on his VPS, about 10 parallel at most.
He added an MCP server to Eagle, the Go backend for his own website. Now he can snap a photo of a cinema ticket and ask the AI to add it to his movies log on the site.
AI agent populates and keeps updating home lab inventory and documentation in Netbox.
He used AI to create a small tool on val.town that automatically syncs his GoodReads updates to BookHive. The val.town blog featured the tool as one of his experiments.
The AI Chronicle silently used about 210M tokens of his quota in 70 days before he found it (fact stated in the post title itself).
The AI built him a Bluesky bot that posts HN Wikipedia articles and posts an archive pick after 48 quiet hours; it is live and posting.
Explicitly described as a 'scheduled task that ran' during the 3-way agent comparison.
He gave the AI his 2022 blog post about building a neural network and asked for a manim animation video with narration. The AI made the video in about 55 minutes, and it also spotted bugs in the original post while converting 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.