Skip to content
corpus.blog
Sign in Claim your blog
Record · joecarlsmith.substack.com

How human-like do safe AI motivations need to be?

joecarlsmith.substack.com · 12 November 2025 · 71 min read

A post on joecarlsmith.substack.com, published 12 November 2025, has not been cited by any blog yet (corpus.blog, measured 11 October 2026).

A record is what was published and who pointed at it. The text of the post is not shown here: read it at the source, or at its Wayback capture.

Read at joecarlsmith.substack.com (opens in a new tab) Wayback capture (opens in a new tab)

0blogs citing

Citing blogs and links by period
Period Blogs Links
All time00
Last 90 days00
Last 30 days00
Last 7 days00
Figures for this page
Words blogs link it with0
External links39
Length16,284

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://joecarlsmithaudio.buzzsprout.com/2034731/episodes/18175429-how-human-like-do-safe-ai-motivations-need-to-be
joecarlsmithaudio.buzzsprout.com
How do we solve the alignment problem? Read at joecarlsmith.com (opens in a new tab)
joecarlsmith.com
https://www.amazon.com/Anyone-Builds-Everyone-Dies-Superhuman/dp/0316595640 Who cites this page
amazon.com
Giving AIs safe motivations Read at joecarlsmith.com (opens in a new tab)
joecarlsmith.com
Controlling the options AIs can pursue Read at joecarlsmith.com (opens in a new tab)
joecarlsmith.com
AI for AI safety Read at joecarlsmith.com (opens in a new tab)
joecarlsmith.com
Can we safely automate alignment research? Read at joecarlsmith.com (opens in a new tab)
joecarlsmith.com
https://www.lesswrong.com/w/nearest-unblocked-strategy Who cites this page
lesswrong.com
Leaving Open Philanthropy, going to Anthropic Read at joecarlsmith.com (opens in a new tab)
joecarlsmith.com
https://x.com/ESYudkowsky/status/1648518676084305926 Who cites this page
x.com
https://en.wikipedia.org/wiki/Sydney_(Microsoft Who cites this page
en.wikipedia.org
Alignment faking in large language models Read at anthropic.com (opens in a new tab)
anthropic.com
Agentic misalignment: How LLMs could be insider threats Read at anthropic.com (opens in a new tab)
anthropic.com
https://arxiv.org/abs/2502.17424 Who cites this page
arxiv.org
Persona vectors: Monitoring and controlling character traits in language models Read at anthropic.com (opens in a new tab)
anthropic.com
https://palisaderesearch.org/blog/shutdown-resistance Who cites this page
palisaderesearch.org
Detecting and reducing scheming in AI models Read at openai.com (opens in a new tab)
openai.com
Towards a Typology of Strange LLM Chains-of-Thought Read at lesswrong.com (opens in a new tab)
lesswrong.com
https://www.arxiv.org/pdf/2509.15541 Who cites this page
arxiv.org
https://www.antischeming.ai/cot-transcripts Who cites this page
antischeming.ai
https://www.antischeming.ai/cot-transcripts/figure-2-sandbag-model-graded-cot Who cites this page
antischeming.ai
https://www.lesswrong.com/posts/EaLCAZ4bgycY6hFC8/value-fragility-and-ai-takeover Who cites this page
lesswrong.com
An even deeper atheism Read at joecarlsmith.com (opens in a new tab)
joecarlsmith.com
What is it to solve the alignment problem? Read at joecarlsmith.com (opens in a new tab)
joecarlsmith.com
https://ifanyonebuildsit.com/11/shutdown-buttons-and-corrigibility Who cites this page
ifanyonebuildsit.com
https://www.lesswrong.com/posts/AFdvSBNgN2EkAsZZA/what-is-it-to-solve-the-alignment-problem-1 Who cites this page
lesswrong.com
When should we worry about AI power-seeking? Read at joecarlsmith.com (opens in a new tab)
joecarlsmith.com
https://arxiv.org/pdf/2311.08379 Who cites this page
arxiv.org
Coherent decisions imply consistent utilities Read at lesswrong.com (opens in a new tab)
lesswrong.com
Why should ethical anti-realists do ethics? Read at joecarlsmith.com (opens in a new tab)
joecarlsmith.com
Problem of fully updated deference Read at lesswrong.com (opens in a new tab)
lesswrong.com
https://www.lesswrong.com/w/ontology-identification-problem Who cites this page
lesswrong.com
4e - Feature Visualization Read at distill.pub (opens in a new tab)
distill.pub
https://ifanyonebuildsit.com/4/if-current-ais-are-mostly-weird-in-extreme-cases-whats-the-problem Who cites this page
ifanyonebuildsit.com
Being nicer than Clippy Read at joecarlsmith.com (opens in a new tab)
joecarlsmith.com
https://www.edge.org/conversation/the-myth-of-ai Who cites this page
edge.org
https://www.lesswrong.com/posts/2NncxDQ3KBDCxiJiP/cosmopolitan-values-don-t-come-free?commentId=sjutYfdA28BaovfPp Who cites this page
lesswrong.com
https://en.wikipedia.org/wiki/Coherent_extrapolated_volition Who cites this page
en.wikipedia.org
On the limits of idealized values Read at joecarlsmith.com (opens in a new tab)
joecarlsmith.com

Something wrong here? Report a problem