# Wired says GPT-6 Sol trained a virtual Microduck to identify cats

- Published: 2026-11-11T19:55:54.000Z
- Updated: 2026-11-12T10:04:10.225Z
- Section: Models
- Topics: Agents, Research
- Page: https://aidailyjournal.com/en/n/2026/11/11/wired-says-gpt-6-sol-trained-a-virtual-microduck-to-identify-cats/
- Sources: [Wired](https://wired.com/story/i-trained-a-microduck-to-be-my-cats-butler)

## Summary

Wired reports that it used OpenAI’s GPT-6 Sol to train a virtual version of Microduck, a robot developed by Pollen Robotics and Hugging Face, to walk around a room and identify Bengal cats. The author says the coding and training took a few hours, using Nous Research’s Hermes agent and an Nvidia DGX Spark as well. The process used Nvidia’s Isaac Sim to control the robot, assess videos of its performance and suggest training adjustments. The model got it to walk without toppling over, but did not properly reproduce a moonwalk.

According to Wired, University of California, Berkeley professor Ken Goldberg used OpenAI’s Astra with Nvidia’s Newton tool to create a 3D simulation of a robot in about an hour. Nvidia researcher Jim Fan says language models can now access models that control physical actions. Fan, Goldberg and others also open sourced the Aspire robotics framework, which lets a robot discover and use new skills.

## Why it matters (editorial interpretation)

Wired’s report suggests a tighter integration between agents, simulation and robotic control: the system assessed videos and recommended adjustments during training. Open-sourcing the Aspire framework could also make it easier for robots to discover and use new skills, although the test still had limitations, such as the incomplete moonwalk.

_Summary written by AI Daily Journal in its own words, based on the sources above. For details, read the original articles._