causal

Profound Ethics Requires High Capability

To be profoundly ethical, an AI must also be very capable—it needs a good world model, a good understanding of ethics, and good reasoning—because you cannot consistently be profoundly ethical without all three; conveniently, world model and reasoning come along as capabilities improve, so the ethical understanding is the part requiring deliberate effort.

causalpending

Speaker

Shane Legg (DeepMind Founder)

Evidence Quote

“if you don't have any of those things, how can you possibly be consistently profoundly ethical? You can't. So we actually need better reasoning, better understanding of the world, and better understanding of ethics in our systems.”

Source

Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:31:07 AM

Your notes

Loading notes...