✳flâneur — a map of the web's best reading
Sum-threshold attacks — LessWrong
lesswrong.com · 11,536 words · saved by 1 readers
How do you affect something far away, a lot, without anyone noticing? …
x Sum-threshold attacks — LessWrong World Modeling Curated 261 Sum-threshold attacks by TsviBT 8th Sep 2023 Linkpost for tsvibt.blogspot.com 13 min read 58 261 How do you affect something far away, a lot, without anyone noticing? (Note: you can safely skip sections. It is also safe to skip the essay entirely, or to read the whole thing backwards if you like.) The frog's lawsuit Attorney for the defendant: "So, Mr. Frog. You allege that my client caused you grievous bodily harm. How is it that you claim he harmed you?" Frog: "Ribbit RIBbit ribbit." Attorney: "Sir..." Frog: "Just kidding. Well,
Explore this link on the map →related reading
- On Seeing Through and Unseeing: The Hacker Mindset · Gwern.netgwern.net
- On Really Trying · Gwern.netgwern.net
- Radimentary | "Everything can be made radically elementary." ~Steven Rudichradimentary.wordpress.com
- Power Lies Trembling: a three-book review — LessWronglesswrong.com
- Taboo Your Words — LessWronglesswrong.com
- Sandbagging with misaligned action - Chain-of-Thought Transcript - Anti-Schemingantischeming.ai
- Focus on the places where you feel shocked everyone's dropping the ball — LessWronglesswrong.com
- How An Algorithm Feels From Inside — LessWronglesswrong.com
- 2312.06942arxiv.org
- Thoughts for Curious Rabbit-holers Like Me [Live Post]blog.aayushg.com
- How can we solve diffuse threats like research sabotage with AI control?blog.redwoodresearch.org
- Catching the Spark — LessWronglesswrong.com