corpus.blog
56,966 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a0e1ef-c76f-71a6-ab4a-3c8c3c13dc04

Paradigms of AI alignment: components and enablers

vkrakovna.wordpress.com · published 2 June 2022

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 vkrakovna.wordpress.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
53
Words captured
2,594

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://drive.google.com/file/d/1DXSum8dVnvmFCLGjLoz4Zmgb_l-KJkj-/view
drive.google.com
https://www.lesswrong.com/posts/JC7aJZjt2WvxxffGz/paradigms-of-ai-alignment-components-and-enablers
lesswrong.com
https://vkrakovna.wordpress.com/ai-safety-resources
vkrakovna.wordpress.com
https://deepmindsafetyresearch.medium.com/building-safe-artificial-intelligence-52f5f75058f1
deepmindsafetyresearch.medium.com
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-1.png
vkrakovna.wordpress.com
https://arxiv.org/abs/1606.06565
arxiv.org
https://ai-alignment.com/iterated-distillation-and-amplification-157debfd1616
ai-alignment.com
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-3.png
vkrakovna.wordpress.com
https://arxiv.org/abs/1810.08575
arxiv.org
https://arxiv.org/abs/1805.00899
arxiv.org
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-2.png
vkrakovna.wordpress.com
https://openai.com/blog/debate/
openai.com
http://alignment.org
alignment.org
https://docs.google.com/document/d/1WwsnJQstPq91_Yh-Ch2XRL8H_EpsnjrC1dwZXR37PC8/edit
docs.google.com
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-4.png
vkrakovna.wordpress.com
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-5.png
vkrakovna.wordpress.com
https://arxiv.org/abs/2105.14111
arxiv.org
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-6.png
vkrakovna.wordpress.com
https://arxiv.org/abs/1906.01820%5C
arxiv.org
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-7.png
vkrakovna.wordpress.com
Zoom In: An Introduction to Circuits Read at the source ↗
distill.pub
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-8.png
vkrakovna.wordpress.com
A Mathematical Framework for Transformer Circuits Read at the source ↗
transformer-circuits.pub
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/induction_head.png
vkrakovna.wordpress.com
https://rome.baulab.info/
rome.baulab.info
https://vkrakovna.wordpress.com/wp-content/uploads/2022/06/eiffel.png
vkrakovna.wordpress.com
https://www.deepmind.com/blog/specification-gaming-the-flip-side-of-ai-ingenuity
deepmind.com
http://tinyurl.com/specification-gaming
tinyurl.com
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/boatrace.gif
vkrakovna.wordpress.com
https://openai.com/blog/faulty-reward-functions/
openai.com
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/robothand-1.gif
vkrakovna.wordpress.com
https://openai.com/blog/deep-reinforcement-learning-from-human-preferences/
openai.com
https://arxiv.org/abs/2201.03544
arxiv.org
https://deepmindsafetyresearch.medium.com/designing-agent-incentives-to-avoid-side-effects-e1ac80ea6107
deepmindsafetyresearch.medium.com
https://arxiv.org/abs/2010.07877
arxiv.org
https://arxiv.org/abs/2006.06547
arxiv.org
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-12.png
vkrakovna.wordpress.com
https://deepmindsafetyresearch.medium.com/designing-agent-incentives-to-avoid-reward-tampering-4380c1bb6cd
deepmindsafetyresearch.medium.com
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-10.png
vkrakovna.wordpress.com
https://arxiv.org/abs/2011.08827
arxiv.org
https://arxiv.org/abs/1912.01683
arxiv.org
https://www.lesswrong.com/s/fSMbebQyR4wheRrvk/p/W22Btd7NmGuucFejc
lesswrong.com
https://www.lesswrong.com/posts/nZY8Np759HYFawdjH/satisficers-tend-to-seek-power-instrumental-convergence-via
lesswrong.com
https://en.wikipedia.org/wiki/Human_Compatible
en.wikipedia.org
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-13.png
vkrakovna.wordpress.com
https://intelligence.org/files/csrbai/hadfield-menell-slides.pdf
intelligence.org
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-16.png
vkrakovna.wordpress.com
https://www.alignmentforum.org/posts/Cd7Hw492RqooYgQAS/progress-on-causal-influence-diagrams
alignmentforum.org
https://www.alignmentforum.org/posts/i3BTagvt3HbPMx6PN/embedded-agency-full-text-version
alignmentforum.org
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-14.png
vkrakovna.wordpress.com
https://www.lesswrong.com/s/ehnG4mseKF6xALmQy/p/vDGvHBDuMtcPd8Lks
lesswrong.com
https://www.lesswrong.com/posts/cy3BhHrGinZCp3LXE/testing-the-natural-abstraction-hypothesis-project-intro
lesswrong.com
https://vkrakovna.wordpress.com/wp-content/uploads/2022/05/image-15.png
vkrakovna.wordpress.com