Context: somebody at some point floated the idea that Ronny might (a) understand the argument coming out of the Quintin/Nora camp, and (b) be able to translate them to Nate. Nate invited Ronny to chat. The chat logs follow, lightly edited.

The basic (counting) argument

Ronny Fernandez

Are you mostly interested in Quintin's newest post?

I haven’t read it but I don’t suspect it's his best

So8res

I'm more interested in something like "what are the actual arguments here".

I'm less interested in "ronny translates for others" and more interested in "what ronny believes after having spoken to others", albeit with a focus on the arguments that others are making that various locals allegedly buy.

Ronny Fernandez

Sweet that's way better

So8res

Options: (a) i start asking questions; (b) you poke me when you wanna chat; (c) you monologue a bit about places where you think you know something i don't

and obviously [...]

---

Outline:

(00:28) The basic (counting) argument

(07:30) Evolution / Reflection Process is Path Dependent

(25:08) Summary and discussion of training an agent in a simulation

(32:02) Alignment problem probably fixable, but likely wont be fixed

(38:11) Discussing whether this argument about training can be formalized

---

First published:
December 19th, 2023

Source:
https://www.lesswrong.com/posts/9x8nXABeg9yPk2HJ9/ronny-and-nate-discuss-what-sorts-of-minds-humanity-is

---

Narrated by TYPE III AUDIO.

“Ronny and Nate discuss what sorts of minds humanity is likely to find by Machine Learning” by habryka, So8res, Ronny Fernandez

LessWrong (30+ Karma)