Evidence receipt / commitment
Published · transcript-backedShane Legg: commitment
26 Oct 2023 Dwarkesh Podcast Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures
“It should preserve them because if it's making all its decisions based on a good understanding of ethics and values, and it's consistent in doing this, it shouldn't take actions which undermine that.”
Source trail
Everything needed to verify it.
- Speaker
- Shane Legg
- Attribution
- Verified speaker
- Claim type
- commitment
- Recorded
- 26 Oct 2023
- Publisher
- Dwarkesh Podcast
Transcript context
…And how do we do that in a way that we can be confident that a super human level model will preserve those values or have learned them in the first place? It should preserve them because if it's making all its decisions based on a good understanding of ethics and values, and it's consistent in doing this, it shouldn't take actions which undermine that. That would be inconsistent. Right, so then how do we get to the point where it has learned them in the first place?…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.