corpus.blog
Claim your blog
Record · corpus.blog/posts/01a10267-b055-7032-8940-704ce2b468a2

Nobody’s on the ball on AGI alignment

forourposterity.com · published 29 March 2023

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at forourposterity.com Wayback capture
1blog citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
29
Words captured
4,024

Cited by 1 blog in 1 post

One row per blog, the most recently citing first. Each shows the blog's newest citing post; open a row for the others.

Blog
Newest citing post
Date
Alexey Guzey1 post
AI Alignment Is Turning from Alchemy Into Chemistry Read at the source ↗
—

Links from this post

Link
Host
https://forum.effectivealtruism.org/posts/3gmkrj3khJHndYGNe/estimating-the-current-and-future-number-of-ai-safety?ref=forourposterity.com
forum.effectivealtruism.org
https://aiindex.stanford.edu/wp-content/uploads/2022/03/2022-AI-Index-Report_Master.pdf
aiindex.stanford.edu
https://www.lesswrong.com/posts/qHCDysDnvhteW7kRd/arc-s-first-technical-report-eliciting-latent-knowledge
lesswrong.com
https://www.alignmentforum.org/s/EmDuGeRw749sD3GKd?ref=forourposterity.com
alignmentforum.org
https://evals.alignment.org/
evals.alignment.org
https://www.anthropic.com/index?subjects=interpretability&ref=forourposterity.com
anthropic.com
https://arxiv.org/abs/2203.02155
arxiv.org
Why I’m optimistic about our alignment approach Read at the source ↗
aligned.substack.com
https://www.anthropic.com/index/core-views-on-ai-safety
anthropic.com
https://www.alignmentforum.org/posts/rCJQAkPTEypGjSJ8X/how-might-we-align-transformative-ai-if-it-s-developed-very
alignmentforum.org
https://www.youtube.com/watch?v=YTlrPeikoyw&ref=forourposterity.com
youtube.com
https://www.cold-takes.com/ai-could-defeat-all-of-us-combined/
cold-takes.com
How we could stumble into AI catastrophe Read at the source ↗
cold-takes.com
https://www.lesswrong.com/posts/j9Q8bRmwCgXRYAgcJ/miri-announces-new-death-with-dignity-strategy
lesswrong.com
https://arxiv.org/abs/2212.03827
arxiv.org
https://www.lesswrong.com/posts/L4anhrxjv8j2yRKKp/how-discovering-latent-knowledge-in-language-models-without
lesswrong.com
http://collinpburns.com/?ref=forourposterity.com
collinpburns.com
https://www.cold-takes.com/
cold-takes.com
http://www.dwarkeshpatel.com
dwarkeshpatel.com
https://www.buzzsprout.com/2073880/12591817-nobody-s-on-the-ball-on-agi-alignment-by-leopold-aschenbrenner?ref=forourposterity.com
buzzsprout.com
https://www.cold-takes.com/most-important-century/
cold-takes.com
https://arxiv.org/abs/2212.08073?ref=bounded-regret.ghost.io
arxiv.org
https://ai-alignment.com/ai-alignment-is-distinct-from-its-near-term-applications-81300500ad2e?ref=forourposterity.com
ai-alignment.com
https://www.alignmentforum.org/posts/pRkFkzwKZ2zfa3R6H/without-specific-countermeasures-the-easiest-path-to
alignmentforum.org
https://www.lesswrong.com/posts/Gc9FGtdXhK9sCSEYu/what-a-compute-centric-framework-says-about-ai-takeoff
lesswrong.com
https://epochai.org/blog/revisiting-algorithmic-progress
epochai.org
https://www.lesswrong.com/posts/pdaGN6pQyQarFHXF4/reward-is-not-the-optimization-target
lesswrong.com
Why Would AI "Aim" To Defeat Humanity? Read at the source ↗
cold-takes.com
https://twitter.com/leopoldasch/status/1639679581308465154?s=46&t=612rWr3QlD0pepiGrqymeg&ref=forourposterity.com
twitter.com
Elsewhere on forourposterity.com (1)