LinearUncle (@LinearUncle) “Ralph 作者分享的一个 GLM-5.2 使用技巧： 他发现 GLM 这类模型有个特点——提示词写得” — TopicDigg

alright it seems people are losing their shit about zai glm being good. it’s been a not to open secret that the best hyper token burning engineers for last six months have been doing statsarb in this window of opportunity whilst western companies have been locking in with either openai or anthropic. the glm models are really fantastic but they are like an autistic german. black and white thinking and high precision. whereas opus/fable are great for painting colours/figuring out with gaps of meaning when under specification of prompts. here’s how you should be using it. use another model (ie gemini) which excels at painting to create the prompts used for generation the prompt which is then put into glm. for those similar with Amp’s oracle pattern. it’s that. register another model in as a tool within GLM itself for quality of living benefits.