corpus.blog
41,554 blogs · 5,181,941 posts Claim your blog
Record · corpus.blog/posts/01a08c66-50d9-7377-a9a3-8f9bd4ac3d36

Alignment Implications of LLM Successes: a Debate in One Act

zackmdavis.net · published 21 October 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 zackmdavis.net Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
39
Words captured
3,993

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://www.lesswrong.com/posts/pYWA7hYJmXnuyby33/alignment-implications-of-llm-successes-a-debate-in-one-act
lesswrong.com
https://www.lesswrong.com/posts/NyFuuKQ8uCEDtd2du/the-genie-knows-but-doesn-t-care
lesswrong.com
https://www.lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators
lesswrong.com
https://arxiv.org/abs/2201.11903
arxiv.org
https://say-can.github.io/
say-can.github.io
https://voyager.minedojo.org/
voyager.minedojo.org
https://github.com/MineDojo/Voyager/blob/55e45a880755d0c8c66ca7fb5fe7962ac8974f89/voyager/prompts/curriculum.txt
github.com
Gwern’s experiments in creative writing with GPT-3
gwern.net
https://www.lesswrong.com/posts/nH4c3Q9t9F3nJ7y8W/gpts-are-predictors-not-imitators
lesswrong.com
https://www.lesswrong.com/posts/htrZrxduciZ5QaCjw/language-models-seem-to-be-much-better-than-humans-at-next
lesswrong.com
https://www.lesswrong.com/posts/WnheMGAka4fL99eae/hindsight-devalues-science
lesswrong.com
https://selfawaresystems.files.wordpress.com/2008/01/ai_drives_final.pdf
selfawaresystems.files.wordpress.com
https://www.lesswrong.com/posts/4ARaTpNX62uaL86j6/the-hidden-complexity-of-wishes
lesswrong.com
https://en.wikipedia.org/wiki/Stochastic_gradient_descent
en.wikipedia.org
https://www.lesswrong.com/posts/4hLcbXaqudM9wSeor/philosophy-in-the-darkest-timeline-basics-of-the-evolution
lesswrong.com
https://www.lesswrong.com/posts/D7PumeYTDPfBTp3i7/the-waluigi-effect-mega-post
lesswrong.com
https://arbital.com/p/not_more_paperclips/
arbital.com
https://www.lesswrong.com/posts/i3BTagvt3HbPMx6PN/embedded-agency-full-text-version
lesswrong.com
https://intelligence.org/files/Corrigibility.pdf
intelligence.org
https://arbital.com/p/foreseeable_difficulties/
arbital.com
https://arbital.com/p/optimized_agent_appears_coherent/
arbital.com
https://udlbook.github.io/udlbook/
udlbook.github.io
https://en.wikipedia.org/wiki/Universal_approximation_theorem
en.wikipedia.org
http://bactra.org/notebooks/nn-attention-and-transformers.html
bactra.org
https://arxiv.org/abs/2306.17844
arxiv.org
https://www.lesswrong.com/posts/jtoPawEhLNXNxvgTT/bing-chat-is-blatantly-aggressively-misaligned
lesswrong.com
https://nostalgebraist.tumblr.com/post/728556535745232896/claude-is-insufferable
nostalgebraist.tumblr.com
https://www.lesswrong.com/posts/cSXZpvqpa9vbGGLtG/thou-art-godshatter
lesswrong.com
https://www.lesswrong.com/posts/gTNB9CQd5hnbkMxAG/protein-reinforcement-and-dna-consequentialism
lesswrong.com
https://www.lesswrong.com/posts/XPErvb8m9FapXCjhA/adaptation-executers-not-fitness-maximizers
lesswrong.com
https://en.wikipedia.org/wiki/Intentional_stance
en.wikipedia.org
https://web.archive.org/web/20071104095534/http://www.overcomingbias.com/2007/11/evolutions-are-.html
web.archive.org
https://www.lesswrong.com/posts/pdaGN6pQyQarFHXF4/reward-is-not-the-optimization-target
lesswrong.com
https://arbital.com/p/value_laden/
arbital.com
https://www.lesswrong.com/posts/esRZaPXSHgWzyB2NL/where-to-draw-the-boundaries
lesswrong.com
https://nickbostrom.com/fut/singleton
nickbostrom.com
https://ordinaryideas.wordpress.com/2015/11/25/two-kinds-of-generalization/
ordinaryideas.wordpress.com
https://www.lesswrong.com/posts/i5kijcjFJD6bn7dwq/evaluating-the-historical-value-misspecification-argument?commentId=E82YzXxvS6nBdCAYc
lesswrong.com
https://www.lesswrong.com/posts/xFotXGEotcKouifky/worlds-where-iterative-design-fails
lesswrong.com