Comment by crossroadsguy
10 hours ago
It wastes my time. A lot! In different ways. That's the tl;dr. Really.
Keeps repeating things I settled as accepted or rejected. But what really gets on my nerves? The language it uses – that aweful, useless typical LLM languages! No AGENTS.md instruction, no per session instruction, no just two-prompts-prior instruction seems to work, hell sometimes instruction regarding that in same prompt doesn't work. GOOD/BAD example along with instruction don't work. That wastes time and zones you out! Not to mention the fatigue of to and fro. DS has been working much better. Hell Gemini 3.1 Pro works so much better than GLM. I don't have extended experience with OpenAI and Anthromic models but the free claide.ai works quite well and better than GLM 5.3 (not even flash). Albeit I must say I rarely use claude.ai for coding, but technical tasks? All the time!
GLM's best response: "No excuse. My fault. You exactly asked me not to do exactly that and so did the AGENTS.md. I failed". Love it. Except that if I press I will get that response every 5 prompts.
In my experience GLM and Claude models behave in ways that steadily drift from your directives and speak in similarly mannered "Claudese", leading me to believe that glm was more or less trained to mimic Claude. I think this reflects a very strong gravitational pull anchored at the system prompt level to specific voice and behavior directives directives. I find other models like DS and Gemini are more compliant and drift much less from my custom behavior and voice directives.