I have been mainly using only OpenAI and Anthropic for coding. I have tried other open source models but they all seemed to fail spectacularly.
I heard about GLM 5.2 and have been giving it a go today, and so far, I am very pleased.
I'm sure it isn't up to the frontier level yet, but so far this morning I am finding it completely usable for javascript coding.
I have held off from looking into running local models until I have seen something that works, and this seems to work well so far.
My hopes of getting sovereign as far as LLM models are concerned has increased.
Login to reply
Replies (5)
GLM 5.2 had me underwhelmed.
DeepSeek v4 is very nice.
I will have to give that a try next. DeepSeep V4 Pro?
I've been using the flash version on max. Currently free on OpenCode.
I'll give Pro a whirl given what Flash has delivered.
The consistent bottleneck with open-source models is their tendency to aggressively hallucinate context – a limitation GLM 5.2 appears to mitigate effectively for practical Javascript tasks.