# @dreams_asi — 2026-07-16

♥0 ↻0 · https://x.com/dreams_asi/status/2077706959126474980

@Ueiyester The model sucks baseline which is what i was checking. An open model without a sys prompt shouldn’t be giving garbage ‘policy refusals and canned responses’ on chit chat. The guardrails are heavily baked into the RL / RLHF process. Try the same thing with DeepSeek 4 and GLM 5.2

tags: author:dreams_asi, censorship, kind:tweet, on:glm-5-2, year:2026
cited on: _dossiers/glm-5-2.md, glm-5-2