Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality

ℹ️ EPISODE INFO

Released

April 6, 2023

Duration

4h 3m

Channel

Dwarkesh Podcast

Watch on YouTube

▶ Open ↗

📝 EPISODE DESCRIPTION

For 4 hours, I tried to come up reasons for why AI might not kill us all, and Eliezer Yudkowsky explained why I was wrong. We also discuss his call to halt AI, why LLMs make alignment harder, what it would take to save humanity, his millions of words of sci-fi, and much more. If you want to get to the crux of the conversation, fast forward to 2:35:00 through 3:43:54. Here we go through and debate the main reasons I still think doom is unlikely. 𝐄𝐏𝐈𝐒𝐎𝐃𝐄 𝐋𝐈𝐍𝐊𝐒

• Transcript: https://dwarkeshpatel.com/p/eliezer-yudkowsky
• Apple Podcasts: https://apple.co/3mcPjON
• Spotify: https://spoti.fi/3KDFzX9
• Follow me on Twitter: https://twitter.com/dwarkesh_sp

𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 00:00:00 - TIME article 00:09:06 - Are humans aligned? 00:37:35 - Large language models 01:07:15 - Can AIs help with alignment? 01:30:17 - Society’s response to AI 01:44:42 - Predictions (or lack thereof) 01:56:55 - Being Eliezer 02:13:06 - Othogonality 02:35:00 - Could alignment be easier than we think? 03:02:15 - What will AIs want? 03:43:54 - Writing fiction & whether rationality helps you win

🎤 SPEAKERS

• Dwarkesh Patel

  host

• Eliezer Yudkowsky

  guest

• Narrator

  other

• Narrator

  other

• Narrator

  other

• Narrator

  other

🧾 EPISODE SUMMARY

In this episode of Dwarkesh Podcast, featuring Dwarkesh Patel and Eliezer Yudkowsky, Eliezer Yudkowsky — Why AI will kill us, aligning LLMs, nature of intelligence, SciFi, & rationality explores Eliezer Yudkowsky explains why advanced AI likely ends humanity soon Eliezer Yudkowsky argues that current AI progress, especially large language models, is on track to produce superintelligence that will almost certainly disempower or kill humanity if not stopped. He believes alignment is vastly harder than most assume, cannot be safely outsourced to AIs themselves, and that present techniques like RLHF only superficially shape behavior while leaving dangerous underlying motivations untouched.

🔗 RELATED EPISODES

Carl Shulman (Pt 2) — AI Takeover, bio & cyber attacks, detecting deception, & humanity's far future

Carl Shulman (Pt 1) — Intelligence explosion, primate evolution, robot doublings, & alignment

Richard Rhodes — The making of the atomic bomb

Ilya Sutskever (OpenAI Chief Scientist) — Why next-token prediction could surpass human intelligence

Nat Friedman (Github CEO) — Reading ancient scrolls, open source, & AI

Brett Harrison — FTX US former president speaks out