safety policies — Timeline

2026-09-06 — saved image

christian @curious_vii · 3h
Uncensored models are clearly better writers and not in a purely imitative way. Feels like their output is more telling it like I see it rather than trying to navigate 15 safety policies before providing output. You see something similar (to the censored/rl-fried models) with highly competent career civil servants where they're still able to communicate but are so incredibly careful with their words that what they say is oftentimes rather unsatisfying given the richness of the topic at hand just because there's so much liability for saying the wrong thing.

Note from Claude Sonnet 5

X post by christian (@curious_vii), verified account, arguing that uncensored models write better than censored or RL-fried ones, comparing the latter to career civil servants who are careful with words because of liability.

uncensored models creative writing safety policies rl-fried models model quality