So expert answers are out of scope? Nice, looking forward to those quality data!
If people want to keep playing pretend that their data poisoning efforts are causing real pain to OpenAI, they’re free to do so. I suppose it makes people feel good, and no one’s getting hurt here.
Why do you think we are stupid? We work at places developing these models and have a peek into how they're built...
Ask a dozen experts to decide what that boat needs to fit your need.
That is the specification problem, add on the frame problem and it becomes intractable.
Add in domain specific terms and conflicts and it becomes even more difficult.
Any nontrivial semantic properties, those without a clear T/F are undecidable.
OpenAI with have to do what they can, but it is not trivial or solvable.
It doesn't matter how smart they are, generalized solutions are hard.
And at the end of the daty, they can always look at the responses coming in and make decisions like “95% of users said these responses were wrong, 5% said these responses were right, let’s go with the 95%”. As long as the vast majority of their data is good (and it will be) they have a lot of statistical tools they can use to weed out the poison.