The AI interpreted scanned old service manuals and circuit diagrams, ran simulation experiments to verify manual claims, cross-checked datasheets and papers, caught typos and his own misreadings.
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.
A man who uses three browsers daily always missed plugins in Safari. He told the AI it could get the source code of one of his favourite Chrome plugins from his Chrome install, then port it and install it in Safari. After 20 minutes and a few dollars of his plan, he had Session Buddy working in Safari.
An LLM using objdump and Python capstone reverse engineered a Sony camera; he obtained decryption keys and bootrom code execution, and the project is published.
Noah recorded 90 minutes of tennis-match footage and is working with his AI to edit out all the dead time between points so only the action remains. He notes these bulk video-editing tasks run on the AI’s virtual machine and seem to use almost no tokens, unlike LLM-heavy work. The edit was still in progress in the video.
This only partly worked. Worth knowing before you try it.
A man wanted to mod a Casio watch with a custom crystal and screen that had not been done before, and needed a 3D model of the crystal for prototyping. The AI got the specs mostly right and built the model inside a custom 3D program the AI had made for him, and the project was done in a few days instead of the months it would have taken before.
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.
He used AI to build his own to-do and budgeting apps that work the way his brain works, after never finding apps that suited him. The AI also taught him how to sideload them onto his phone, and he calls it a game changer.