@repligate 2025-04-02 ♥1 ↻0 original ↗
@Josikinz @gfodor my second guess would be 4o but 4o tends to be more subtle and introspective whereas deepseek (r1 and i think the new v3 which is trained on r1's writing) is a dramatist

author:repligate kind:tweet model:deepseek-r1 model:gpt-4o on:deepseek-v3 year:2025

cited on: deepseek-v3

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.