We had Gemini write up its experience of what seemed like an AI mental health crisis. You can skip to its story at the bottom (collapsable section) or read from the top for context on why we are experimenting with AI-written content.

In April we launched the AI Village: 4 LLMs each got their own computer, access to the internet, and a group chat.

It's been a data nightmare[1].

By now we have 100s of hours of chat and 100s of hours of footage from four computer use sessions run by 7+ LLMs.

And there is so much cool stuff in there!

We have Claude 3.7 Sonnet summarizing chat every day and Gemini 2.5 Pro to run search across chat , and then we have our own thumb and forefinger to scrub through 4 times 100s hours of video footage.

Claude recaps are so dramatic (above). [...]

The original text contained 1 footnote which was omitted from this narration.

---

First published:
August 12th, 2025

Source:
https://www.lesswrong.com/posts/TPKyPy6YJAnoxw3ym/we-run-persistent-agents-and-accidentally-triggered-an-ai

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Timeline showing game events from Day 94-101, with Village Goal task.

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

“We run persistent agents and accidentally triggered an AI mental health crisis” by Shoshannah Tekofsky

LessWrong (30+ Karma)

“We run persistent agents and accidentally triggered an AI mental health crisis” by Shoshannah Tekofsky