At a recent meetup, a room of about 55 people was asked: do you know every line of code you shipped to production?

One person raised their hand: Chris.

That moment became the center of this episode. Not because AI-assisted coding is bad, but because it exposes the real risk: developers are starting to trust AI-generated output without fully owning it.

In this episode, Miriah, Chris, and Matt talk about AI psychosis: the slow offloading of judgment, skepticism, and responsibility to systems that sound confident by design. We dig into AI slop, sycophantic models, no-slop.ai, Mitchell Hashimoto’s warning about companies operating under AI psychosis, and why “Claude wrote it” is not a defense when production breaks.

This is not an anti-AI episode. We use AI constantly. The point is to stop treating AI like an oracle and start treating it like a tool that needs constraints, review, and ownership.

Topics:

The 1-of-55 meetup story
What AI psychosis means for developers
Who owns AI-generated code?
Why confident output is not the same as correct output
no-slop.ai and the rule: don’t send AI output you haven’t read
Mitchell Hashimoto on AI psychosis in companies
Why arguing with AI usually wastes time
How sycophantic models pull users into the spiral
Practical ways to keep AI honest
Why smaller or self-hosted models can make AI feel less magical

Links:

no-slop.ai: https://no-slop.ai
Mitchell Hashimoto post: https://x.com/mitchellh/status/2055380239711457578
Timnit Gebru post on AI psychosis: https://www.linkedin.com/posts/timnit-gebru-7b3b407_surviving-ai-psychosis-activity-7454588079467593729-X1eT
HBR trendslop article: https://hbr.org/2026/03/researchers-asked-llms-for-strategic-advice-they-got-trendslop-in-return
Patreon: https://patreon.com/DomesticatingAIPodcast
YouTube: https://www.youtube.com/@DomesticatingAI
Apple Podcasts: https://podcasts.apple.com/us/podcast/domesticating-ai/id1873338950
Spotify: https://open.spotify.com/show/2WsAR4fvcXzp3vVZGVlkE2

Keep your AI on a leash.