Record · joecarlsmith.substack.com

Giving AIs safe motivations

joecarlsmith.substack.com · 18 August 2025 · 67 min read

A post on joecarlsmith.substack.com, published 18 August 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 Wayback capture

0blogs citing

Citing blogs and links by period
Period	Blogs	Links
All time	0	0
Last 90 days	0	0
Last 30 days	0	0
Last 7 days	0	0

Figures for this page
Words blogs link it with	0
External links	31
Length	15,198

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://joecarlsmithaudio.buzzsprout.com/2034731/episodes/17686921-giving-ais-safe-motivations Who cites this page

joecarlsmithaudio.buzzsprout.com

How do we solve the alignment problem? Read at joecarlsmith.com

joecarlsmith.com

What is it to solve the alignment problem? Read at joecarlsmith.com

joecarlsmith.com

AI for AI safety Read at joecarlsmith.com

joecarlsmith.com

Can we safely automate alignment research? Read at joecarlsmith.com

joecarlsmith.com

When should we worry about AI power-seeking? Read at joecarlsmith.com

joecarlsmith.com

https://www.lesswrong.com/posts/qs7SjiMFoKseZrhxK/on-first-critical-tries-in-ai-alignment?ref=danmackinlay.name Who cites this page

lesswrong.com

https://www.lesswrong.com/posts/h7QETH7GMk9HcMnHH/the-no-sandbagging-on-checkable-tasks-hypothesis Who cites this page

lesswrong.com

https://ai-alignment.com/training-robust-corrigibility-ce0e0a3b9b4d Who cites this page

ai-alignment.com

Agentic misalignment: How LLMs could be insider threats Read at anthropic.com

anthropic.com

Alignment faking in large language models Read at anthropic.com

anthropic.com

Automated Auditing Read at alignment.anthropic.com

alignment.anthropic.com

https://arxiv.org/pdf/2507.11473 Who cites this page

arxiv.org

https://www.lesswrong.com/posts/5hApNw5f7uG8RXxGS/the-open-agency-model Who cites this page

lesswrong.com

https://arxiv.org/abs/2310.18512 Who cites this page

arxiv.org

https://situational-awareness.ai/superalignment/ Who cites this page

situational-awareness.ai

On the Biology of a Large Language Model Read at transformer-circuits.pub

transformer-circuits.pub

https://arxiv.org/abs/2502.17424 Who cites this page

arxiv.org

https://arxiv.org/abs/2311.08379 Who cites this page

arxiv.org

https://arxiv.org/pdf/2311.08379 Who cites this page

arxiv.org

https://redwoodresearch.substack.com/p/two-proposed-projects-on-abstract Who cites this page

redwoodresearch.substack.com

https://www.lesswrong.com/posts/ChDH335ckdvpxXaXX/model-organisms-of-misalignment-the-case-for-a-new-pillar-of-1 Who cites this page

lesswrong.com

https://www.lesswrong.com/posts/GE6pcmmLc3kdpNJja/fuzzing-llms-sometimes-makes-them-reveal-their-secrets Who cites this page

lesswrong.com

https://www.lesswrong.com/posts/CXYf7kGBecZMajrXC/validating-against-a-misalignment-detector-is-very-different Who cites this page

lesswrong.com

Putting up Bumpers Read at alignment.anthropic.com

alignment.anthropic.com

Evaluating the historical value misspecification argument Read at lesswrong.com

lesswrong.com

https://www.amazon.com/Superintelligence-Dangers-Strategies-Nick-Bostrom/dp/0198739834 Who cites this page

amazon.com

https://intelligence.org/files/ComplexValues.pdf Who cites this page

intelligence.org

https://www.amazon.com/Human-Compatible-Artificial-Intelligence-Problem-ebook/dp/B07N5J5FTS Who cites this page

amazon.com

https://www.aaas.org/membership/member-spotlight/how-design-ai-right-according-aaas-fellow-stuart-russell Who cites this page

aaas.org

Discussion with Nate Soares on a key alignment difficulty Read at lesswrong.com

lesswrong.com

Elsewhere on joecarlsmith.substack.com (1)

What is it to solve the alignment problem? Read at joecarlsmith.substack.com

joecarlsmith.substack.com

Something wrong here? Report a problem