After using the latest version of Claude Code and being surprised how capable it's become while still behaving friendly and corrigibly, I wanted to reflect on how this new observation should update my world model and my P(Doom).

So I reached out to Dr. @Steven Byrnes, the highly polymathic AGI safety researcher who I last interviewed in August about Brain-like AGI, foom & doom, and solving technical alignment.

We discussed:

Steve's high P(Doom)
“Brainlike AGI”: A qualitatively different next-generation AI
Does nearly full unemployment likely come before or after the next ASI regime?
Is “country of geniuses in a data center” a good prediction?
Why we should expect ruthless sociopathic ASI
Post-training & RLVR: the "thin layer" of consequentialism
The air travel vs. space travel analogy

Video & Audio

The episode is available on Substack, YouTube, or by searching “Doom Debates“ in your podcast app.

Transcript

Introduction

Liron 00:00:48
Welcome to Doom Debates. Today, we’ve got a fan favorite returning to the show, Dr. Steven Byrnes. You may remember him from six months ago. We had a really long, enriching conversation that I highly recommend. It's one of my favorite episodes of all time.

He is an [...]

---

Outline:

(01:07) Video & Audio

(01:20) Transcript

(01:23) Introduction

(05:42) Research Update: Whats New in The Last 6 Months

(09:59) The Rise of AI Agents

(17:16) Whats Your P(Doom)?™

(20:50) Brain-Like AGI: The Next Generation of AI

(37:00) Can LLMs Ever Match the Human Brain?

(43:47) Will AI Kill Us Before It Takes Our Jobs?

(49:29) Country of Geniuses in a Data Center

(01:03:19) Why We Should Expect Ruthless Sociopathic ASI

(01:12:58) Post-Training & RLVR -- A Thin Layer of Real Intelligence

(01:30:35) Consequentialism and the Path to Superintelligence

---

First published:
March 10th, 2026

Source:
https://www.lesswrong.com/posts/TwPFvNNayQvLAGkSx/interview-with-steven-byrnes-on-his-mainline-takeoff

---

Narrated by TYPE III AUDIO.

“Interview with Steven Byrnes on His Mainline Takeoff Scenario” by Liron

LessWrong (30+ Karma)