I can't tell what you mean. Can you elaborate?
I think this comment would be better placed as a reply to the post that I'm linking. Perhaps you should put it there?
My summary: Give gifts using the parts of your world-model that are strongest. Usually the answer isn't going to end up being based on your understanding of their hobby.
Window AC units don't actually pull air from outside.
Hey, I've been looking into air quality quite a bit recently. I have several questions.
What air quality sensor are you using? How are you getting outdoor data?
I suspect some of the confusion in the results may be due to circulation within the home and monitor placement. Have you thought much about circulation?
Additionally, it looks like indoor PM2.5 is tracking outdoor PM2.5. Have you thought much about other sources of ventilation?
It doesn't sound hard at all. The things Gwern is describing are the same sort of thing that people do for interpretability where they, eg, find an image that maximizes the probability of the network predicting a target class.
Of course, you need access to the model, so only OpenAI could do it for GPT-3 right now.
I've was thinking along similar lines!
From my notes from 2019-11-24: "Deontology is like the learned policy of bounded rationality of consequentialism"
I wasn't replying to Quintin