Uncensored models are better writers — safety guardrails make output bland
curious_vii · x · 2026-09-06
The author argues uncensored models are clearly better writers — output feels like telling it like they see it, rather than navigating 15 safety policies first. He likens censored/RL-fried models to competent career civil servants: careful to a fault, with unsatisfying output given the richness of the topic.
More from Models
- Astra's release triggered a breakout weekend of AI-CAD: from rebuilding SF landmarks to multi-tool 3D workflows — burhop · 2026-09-06
- Dan Jeffries: embedded reasoning will kill the CoT-distillation accusations against Chinese models — Dan_Jeffries1 · 2026-09-06
- Alexandr Wang urges users to try Muse Spark 1.3 max, called 'Opus-level' by users — alexandr_wang · 2026-09-06
- Models would rather edit files with raw Python than use edit tools — xeophon · 2026-09-06
- ChatGPT agent can click through 'I'm not a robot' checks, reigniting AI security debate — GaelVaroquaux · 2026-09-06
- Astra's language beats Sol by a mile: less QA jargon, docs worth actually sharing — raskingballs · 2026-09-06