"Security Mindset: Lessons from 20+ years of Software Security Failures Relevant to AGI Alignment" by elspood

https://www.lesswrong.com/posts/Ke2ogqSEhL2KCJCNx/security-mindset-lessons-from-20-years-of-software-security

Background

I have been doing red team, bl…

3 years, 7 months ago

View Episode

"Where I agree and disagree with Eliezer" by Paul Christiano

https://www.lesswrong.com/posts/CoZhXrhpQxpy9xw9y/where-i-agree-and-disagree-with-eliezer#fnh5ezxhd0an

by paulfchristiano, 20th Jun 2022. 

Crosspost…

3 years, 8 months ago

View Episode

"Six Dimensions of Operational Adequacy in AGI Projects" by Eliezer Yudkowsky

https://www.lesswrong.com/posts/keiYkaeoLHoKK4LYA/six-dimensions-of-operational-adequacy-in-agi-projects

by Eliezer Yudkowsky

Editor's note:  The fo…

3 years, 8 months ago

View Episode

"Moses and the Class Struggle" by lsusr

https://www.lesswrong.com/posts/pL4WhsoPJwauRYkeK/moses-and-the-class-struggle

"𝕿𝖆𝖐𝖊 𝖔𝖋𝖋 𝖞𝖔𝖚𝖗 𝖘𝖆𝖓𝖉𝖆𝖑𝖘. 𝕱𝖔𝖗 𝖞𝖔𝖚 𝖘𝖙𝖆𝖓𝖉 𝖔𝖓 𝖍𝖔𝖑𝖞 𝖌𝖗𝖔𝖚𝖓𝖉," said the bush.…

3 years, 8 months ago

View Episode

"Benign Boundary Violations" by Duncan Sabien

https://www.lesswrong.com/posts/T6kzsMDJyKwxLGe3r/benign-boundary-violations

Recently, my friend Eric asked me what sorts of things I wanted to have…

3 years, 8 months ago

View Episode

"AGI Ruin: A List of Lethalities" by Eliezer Yudkowsky

https://www.lesswrong.com/posts/uMQ3cqWDPHhjtiesc/agi-ruin-a-list-of-lethalities

  Crossposted from the AI Alignment Forum. May contain more tec…

3 years, 8 months ago

View Episode