corpus.blog
41,554 blogs · 4,969,865 posts Claim your blog
Record · corpus.blog/posts/01a0c569-535e-725e-abb5-167476e61eb2

Shah and Yudkowsky on alignment failures

intelligence.org · published 2 March 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 intelligence.org Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
34
Words captured
27,505

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://www.lesswrong.com/s/n945eovrA3oDueqtq
lesswrong.com
https://www.alignmentforum.org/posts/3vFmQhHBosnjZXuAJ/an-171-disagreements-between-alignment-optimists-and
alignmentforum.org
https://www.lesswrong.com/posts/34Gkqus9vusXRevR8/late-2021-miri-conversations-discussion-and-ama
lesswrong.com
https://www.lesswrong.com/s/n945eovrA3oDueqtq/p/hwxj4gieR7FWNwYfa
lesswrong.com
https://en.wikipedia.org/wiki/Reflexivity_(social_theory
en.wikipedia.org
https://en.wikipedia.org/wiki/Self-organization
en.wikipedia.org
https://www.alignmentforum.org/posts/fkLYhTQteAu5SinAc/corrigibility
alignmentforum.org
https://mailchi.mp/bbd47ba94e84/alignment-newsletter-35
mailchi.mp
https://arbital.com/p/nearest_unblocked/
arbital.com
https://arxiv.org/abs/1706.03741
arxiv.org
https://www.lesswrong.com/posts/7im8at9PmhbT4JHsW/ngo-and-yudkowsky-on-alignment-difficulty
lesswrong.com
https://arxiv.org/abs/1606.03137
arxiv.org
https://arbital.com/p/updated_deference/
arbital.com
https://arbital.com/p/cev/
arbital.com
https://arxiv.org/abs/1906.01820
arxiv.org
https://arbital.com/p/low_impact/
arbital.com
https://arbital.com/p/soft_optimizer/
arbital.com
https://arbital.com/p/shutdown_problem/
arbital.com
https://arbital.com/p/abortable/
arbital.com
https://arbital.com/p/behaviorist/
arbital.com
https://arbital.com/p/conservative_concept/
arbital.com
https://deepmindsafetyresearch.medium.com/scalable-agent-alignment-via-reward-modeling-bf4ab06dfd84
deepmindsafetyresearch.medium.com
https://jan.leike.name/publications/Towards%20Interactive%20Inverse%20Reinforcement%20Learning%20-%20Armstrong,%20Leike%202016.pdf
jan.leike.name
https://arxiv.org/abs/2004.13654
arxiv.org
https://www.tomeveritt.se/papers/alignment.pdf
tomeveritt.se
https://arbital.com/p/dwim/
arbital.com
https://arbital.com/p/task_goal/
arbital.com
https://www.lesswrong.com/s/qWoFR4ytMpQ5vw3FT
lesswrong.com
https://www.lesswrong.com/posts/k7oxdbNaGATZbtEg3/redwood-research-s-current-project
lesswrong.com
https://www.lesswrong.com/tag/lottery-ticket-hypothesis
lesswrong.com
https://www.lesswrong.com/tag/dath-ilan
lesswrong.com
https://astralcodexten.substack.com/
astralcodexten.substack.com
https://www.lesswrong.com/posts/Nwgdq6kHke5LY692J/alignment-by-default
lesswrong.com
https://www.lesswrong.com/posts/CpvyhFy9WvCNsifkY/discussion-with-eliezer-yudkowsky-on-agi-interventions
lesswrong.com
Elsewhere on intelligence.org (3)