I did a podcast with Zvi after seeing that Shane Legg couldn't answer a straightforward question about deceptive alignment on a podcast. Demis Hassabis was recently interviewed on the same podcast and also doesn't seem able to answer a straightforward question about alignment. OpenAI's "Superalignment" plan is literally to build AGI and have it solve alignment for us. The public consensus seems to be that "alignment" is a mysterious pre-paradigmatic field with a lot of [open problems](https://www.great
Guillaume Martres smarter
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import sbt.Keys.* | |
| import sbt.* | |
| import scala.collection.compat.* | |
| /** | |
| * This plugin prints which source files are compiled and why | |
| * */ | |
| object ZincAnalysis extends AutoPlugin { |
JD-P
/ agent_foundations_llms.md
Last active
September 16, 2025 21:42
On Distributed AI Economy Excerpt