A statistician had argued that class balancing helps mini batch gradient descent. He had the AI Astra design and run a simulation to test the claim, and the results partly corrected him: oversampling sped convergence but hurt probability accuracy, while importance weighted oversampling kept most of the speed and the accuracy. The code was cross checked with AI, and he posted the corrected conclusion as an answer.
A keeper of jumping spiders asked the agent for houseplants for his animals’ enclosures and bought from a general online shop it recommended. The agent never checked whether the seller treats its plants. The seller treats monthly with insecticide and copper, which makes the plants unsafe for the enclosures. About $60 of plants were unusable, and he lost time arranging a refund.
$60at stake
This one went wrong. See what happened before you try it.
He set up an AI that wakes up when a new the AI release lands. It reads the changelog, picks out only the parts he cares about, and sends him a DM when there is something of interest.
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.
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 built a Command and Conquer style real time strategy game called Battle Drones, mainly using AI. The game runs in the browser and includes device to device multiplayer over an audio link.