alt Hacker NewsIt's probably fuzzily fixable by including instruction authority levels in the training data. Can't expect much more than that, given that the model itself is fuzzy.
It's probably fuzzily fixable by including instruction authority levels in the training data. Can't expect much more than that, given that the model itself is fuzzy.
We've already seen that it's possible to trick models into seeing user input as their own "thinking" if you make it sound like what the model writes. While it may appear that it's looking at the tags on the input, in practice that's not as strong a guarantee as you'd hope.