corpus.blog
41554 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a07df0-028e-7109-a519-2e75f5a25ed5

Value generalisation Theory of Change: the theory behind the approach

AI Alignment Forum · published 28 August 2026

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 alignmentforum.org Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
25
Words captured
3,254

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://www.alignmentforum.org/s/EYgCdcxsn73fKWWra/p/58zFSWp8Tmxij6ckK
alignmentforum.org
https://www.lesswrong.com/posts/esRZaPXSHgWzyB2NL/where-to-draw-the-boundaries
lesswrong.com
https://www.alignmentforum.org/posts/k54rgSg7GcjtXnMHX/model-splintering-moving-from-one-imperfect-model-to-another
alignmentforum.org
https://arxiv.org/abs/1105.3821
arxiv.org
https://www.lesswrong.com/posts/EbFABnst8LsidYs5Y/goodhart-taxonomy
lesswrong.com
https://arxiv.org/abs/1803.04585
arxiv.org
https://www.sciencedirect.com/science/article/abs/pii/0167278990900876
sciencedirect.com
https://www.alignmentforum.org/posts/SnKfFscgC8Nj5ddi3/classical-symbol-grounding-and-causal-graphs
alignmentforum.org
https://www.lesswrong.com/posts/EEPdbtvW8ei9Yi2e8/bridging-syntax-and-semantics-empirically
lesswrong.com
https://www.lesswrong.com/posts/vXzM5L6njDZSf4Ftk/defining-ai-wireheading
lesswrong.com
https://www.anthropic.com/research/emergent-misalignment-reward-hacking
anthropic.com
https://arxiv.org/abs/1312.6199
arxiv.org
https://arxiv.org/abs/1412.6572
arxiv.org
https://forum.effectivealtruism.org/topics/perverse-instantiation
forum.effectivealtruism.org
https://arxiv.org/abs/2412.03556
arxiv.org
https://www.anthropic.com/news/disrupting-AI-espionage
anthropic.com
https://www.alignmentforum.org/posts/TZgezuYjkfMQxyqJC/value-generalisation-2-the-missing-hole-in-ais-abilities
alignmentforum.org
https://ora.ox.ac.uk/objects/uuid:ce99b73c-07f9-4607-b964-25a03206c6dd/files/m19fd446d1fdcaaf559cf637af22a4c4a
ora.ox.ac.uk
https://www.auai.org/uai2016/proceedings/papers/68.pdf
auai.org
https://arxiv.org/abs/1705.10720
arxiv.org
https://intelligence.org/files/Corrigibility.pdf
intelligence.org
https://gwern.net/tool-ai
gwern.net
https://www.lesswrong.com/w/scalable-oversight
lesswrong.com
https://www.lesswrong.com/posts/gjezyLLaDAzp4DsDB/alignment-can-improve-generalisation-through-more-robustly
lesswrong.com
https://arxiv.org/abs/2309.16166
arxiv.org