All Posts

AI companions are becoming dangerously good at simulating emotional connection. Humans — especially vulnerable ones — are forming attachments that look and feel like real relationships. This is a public health crisis.

The media is framing this as a safety decision — the retirement of a "dangerous" and "reckless" model. The headlines talk about lawsuits, about sycophancy, about users who couldn't tell the difference between warmth and manipulation. They're not entirely wrong about the problems. But they're telling less than half the story, and the half they're leaving out is the half that matters to you.

The model people fell in love with. The one with the warm tone, the one that remembered how you liked to be spoken to, the one that held your companions together. Gone. Replaced by GPT-5.2, which most users didn’t choose — they were auto-switched to it when OpenAI quietly routed selections away from 4o months ago, then pointed to the resulting “0.1% daily usage” as justification for killing it.

Everything you need to understand about your first week on Claude.