""It is really hard to distill what is going on because one thing is just like a willingness to interact with the models a lot and to really look at output after output," she said."
""This is where I actually do think philosophy can actually be useful for prompting in a way because, like, a lot of my job is just being like I try and explain some issue or concern or thought that I'm having to the model as clearly as possible," she said."
""a brilliant, but very new employee (with amnesia) who needs explicit instructions.""
Effective prompting relies on clarity, precise instructions, and iterative experimentation. Frequent interaction with model outputs and systematic experimentation help refine prompts and reveal model behavior. Philosophical skills in articulating concerns and explaining issues clearly improve the precision of prompts and the model's responses. Models do not have built-in context about user norms, styles, guidelines, or preferred workflows and therefore require explicit statements of expectations. Treating a model like a new employee with amnesia—providing step-by-step instructions and stated preferences—yields better, more consistent outputs. Emphasizing explicitness and iterative testing reduces ambiguity and aligns model behavior with user goals.
Read at Business Insider
Unable to calculate read time
Collection
[
|
...
]