Daniel_Friedrich answers What posts would you like someone to write?

[Daniel_Friedrich]

I’d like to see

1. an overview of simple AI safety concepts and their easily explainable real-life demonstrations

   1. For instance, to explain sycophancy, I tend to mention the one random finding from this paper that hallucinations are more frequent, if a model deems the user uneducated

2. more empirical posts on near-term destabilization (concentration of power, super-persuasion bots, epistemic collapse)