Quoting seangoedecke.com:

Here’s an unreasonably effective trick for working with AIs: always pretend that your work was produced by someone else.

Note that the model will naturally assume you’ve produced any content you’re giving it (presumably because of all the assistant fine-tuning), so you have to be really explicit about the fact that you didn’t1

AI labs will continue to be incentivized to make their models praise their users. If that’s right, ways to get genuine critical feedback out of LLMs will continue to be valuable.