Comment by cooper_ganglia
13 hours ago
From the article:
> Specifying an objective to the model is not enough. Directing how the work is constructed is what counts.
13 hours ago
From the article:
> Specifying an objective to the model is not enough. Directing how the work is constructed is what counts.
That still sounds incredibly vague and open for interpretation. For example, is setting up md files defining how you want things to be written enough?
That's interesting but how is anyone supposed to prove it? They would have to get their hands on your prompts.
> They would have to get their hands on your prompts
Unless you are running a local model, your prompts are almost certainly logged by your inference provider, and would only be a subpoena away?
Leaks, whistleblowers. Some circumstantial evidence will also do if there's enough of it. Like having hallucinated parts of code that do absolutely nothing, and can't be explained as e.g. leftovers from a refactor.