Record · corpus.blog/posts/01a08774-99b9-701c-ab8f-f8ba2d62a6dc

Against LLM Reductionism

erichgrunewald.com · published 8 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 erichgrunewald.com Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
External links: 27
Words captured: 7,204

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://gwern.net/scaling-hypothesis

gwern.net

https://garymarcus.substack.com

garymarcus.substack.com

https://garymarcus.substack.com/p/what-does-it-mean-when-an-ai-fails

garymarcus.substack.com

https://slatestarcodex.com/2019/02/19/gpt-2-as-step-toward-general-intelligence

slatestarcodex.com

https://slatestarcodex.com/2019/02/18/do-neural-nets-dream-of-electric-hobbits/

slatestarcodex.com

https://www.lesswrong.com/posts/WBdvyyHLdxZSAMmoz/taboo-your-words

lesswrong.com

https://github.com/hendrycks/math?ref=bounded-regret.ghost.io

github.com

A Mathematical Framework for Transformer Circuits Read at the source ↗

transformer-circuits.pub

Reverse Engineering a Neural Network's Clever Solution to Binary Addition Read at the source ↗

cprimozic.net

https://www.alignmentforum.org/posts/N6WM6hs7RQMKDhYjB/a-mechanistic-interpretability-analysis-of-grokking

alignmentforum.org

https://thegradient.pub/othello/

thegradient.pub

https://www.lesswrong.com/posts/Neh76ueECviJ6p75o/large-language-models-learn-to-represent-the-world

lesswrong.com

https://archive.is/zyEP1

archive.is

https://twitter.com/sama/status/1631421715434831872

twitter.com

https://www.alignmentforum.org/posts/aEjckcqHZZny9L2zy/emergent-deception-and-emergent-optimization

alignmentforum.org

https://forum.effectivealtruism.org/posts/tCkBsT6cAw6LEKAbm/scoring-forecasts-from-the-2016-expert-survey-on-progress-in

forum.effectivealtruism.org

https://www.alignmentforum.org/posts/QL7J9wmS6W2fWpofd/but-is-it-really-in-rome-an-investigation-of-the-rome-model

alignmentforum.org

https://www.alignmentforum.org/posts/sdxZdGFtAwHGFGKhg/truthful-and-honest-ai

alignmentforum.org

https://garymarcus.substack.com/p/nonsense-on-stilts

garymarcus.substack.com

https://archive.is/OV88I

archive.is

https://medium.com/@experiential.ai/written-recap-ieai-hosts-on-the-dangers-of-stochastic-parrots-with-emily-m-bender-9f0c597aabec

medium.com

https://twitter.com/emilymbender/status/1598161759562792960?s=20&t=_4DUnTbmpbANAIJNnXbEJQ

twitter.com

https://dailynous.com/2023/03/02/multimodal-llms-are-here/

dailynous.com

https://bounded-regret.ghost.io/future-ml-systems-will-be-qualitatively-different/ Read at the source ↗

bounded-regret.ghost.io

https://bounded-regret.ghost.io/emergent-deception-optimization/ Read at the source ↗

bounded-regret.ghost.io

https://matthewbarnett.substack.com/p/a-reply-to-michael-huemer-on-ai

matthewbarnett.substack.com

https://openreview.net/forum?id=gJcEM8sxHK

openreview.net