Zach Maas is an independent AI safety & mechanistic interpretability researcher in Boulder, Colorado, funded by Coefficient Giving. Today Zach joined us to talk about some of his recent work tracing introspection across model depth. This is, I think, the first mech interp talk we've hosted other than ChessGPT, and it was a good one! We hope you enjoy it as much as we did!
Podden och tillhörande omslagsbild på den här sidan tillhör
Max von Hippel. Innehållet i podden är skapat av Max von Hippel och inte av,
eller tillsammans med, Poddtoppen.
