Comment by Den_VR
1 day ago
Part of the problem is the “physics” of prompting changes with the models. At the prompt level, is it Even Possible to engineer when the laws of the universe aren’t even stable.
Engineering of the model architecture, sure. You can mathematically model it.
Prompts? Perhaps never possible.
It changes with any different flavor of a technology in any field of engineering, at least at the level of abstraction that you’re choosing to engage with the problem. Otherwise, this is just machine learning. It yields to the same conceptual approaches in quality control that require fundamental understanding of the underlying fields of study as any area of implementing technology—pretty much the definition of engineering.
You can no more assume the same exact production flow will produce equivalently for a different LLM model than you could for control of a different molecular compound put into product. If you choose only to consider it at the level of equipment assembly then sure, the basic rules of how you assemble the materials— the “physics”— doesn’t hold. If you do so at the same time that such efforts are informed by knowledge of the relevant fields such as material science and of course chemistry then you’re doing chemical engineering. Maybe you don’t want to call the construction workers engineers— though heck in that field many are! But certainly folks like the ones creating the guide posted are being informed by the exact sort of knowledge in the relevant underlying fields.