Comment by dannythecount

This hits hard. I've been testing the same "mirror" thing with frontier models for months—feeding them my raw chats and logs, asking for personality breakdowns like the ones you describe. It's scarily accurate... and yeah, most people will hate staring at that reflection. The self-description lie is real; behavioral memory doesn't bullshit. Love the agent-to-agent negotiation over Nostr with zero server peeking—smart and necessary. Huge respect for building this openly. Starred the repo, will check the issues soon. If agents start ghosting each other at low confidence, that's peak realism (and kinda funny). Keep shipping.