[prologic]

I don't think so. Having build a custom agent with Anthrpic's SDK (in Go) and even running the agent on smaller quantized (non-frontier) models using Ollama, I seriously doubt you'd get good results. I read the same blog post, and I get the impression that the larger model with greater capabilities is able to infer more accurately without being constrained by large(r) system prompts, but I don't think this works so well for smaller less capable models.

[ubermon]

yes. I think there is a threshold of some sort where if a model pass it can tolerate less system prompts. For example, same short prompt could work with deepseek v4 flash but not so much with Qwen 3.6 27B.