corpus.blog
41,554 blogs · 5,149,205 posts Claim your blog
Record · corpus.blog/posts/01a0b61b-4846-7001-b39b-b35613e7ccd7

Risk-Averse AIs

forethought.org · published 23 June 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 forethought.org Wayback capture
1blogs citing
First cited
26 Jun 2026
Most recent
26 Jun 2026
Rank this month
not ranked
External links
114
Words captured
21,232

Cited by

Blog
In the post
Date
Ben Matthews - Free tools and articles for freelance consultants
Saved links: week of 19 June 2026 Read at the source ↗
26 Jun 2026

Links from this post

Link
Host
https://pinecast.com/listen/c2a021f6-80b2-46e2-881c-0dd9547d8e91
pinecast.com
https://www-cdn.anthropic.com/d0636f72a9493d279ed36b33987da3430bcb5911/claudes-constitution_webPDF_26-02.02a.pdf
www-cdn.anthropic.com
https://www.researchgate.net/profile/Philippe-Mongin/publication/284587658_Expected_utility_theory/links/5c934614a6fdccd4602e4df1/Expected-utility-theory.pdf
researchgate.net
https://alignmentproject.aisi.gov.uk/research-area/empirical-investigations-into-ai-monitoring-and-red-teaming
alignmentproject.aisi.gov.uk
https://aclanthology.org/2022.findings-emnlp.423/
aclanthology.org
https://www.anthropic.com/research/exploring-model-welfare
anthropic.com
https://guive.substack.com/p/the-case-for-ai-property-rights
guive.substack.com
https://www.lesswrong.com/posts/vxfEtbCwmZKu9hiNr/proposal-for-making-credible-commitments-to-ais
lesswrong.com
http://arxiv.org/abs/2512.19027
arxiv.org
http://arxiv.org/abs/2204.05862
arxiv.org
http://arxiv.org/abs/2212.08073
arxiv.org
http://arxiv.org/abs/2503.11926
arxiv.org
https://forum.effectivealtruism.org/posts/4LNiPhP6vw2A5Pue3/consider-granting-ais-freedom
forum.effectivealtruism.org
https://www.alignmentforum.org/posts/YsFZF3K9tuzbfrLxo/counting-arguments-provide-no-evidence-for-ai-doom
alignmentforum.org
http://arxiv.org/abs/2410.21514
arxiv.org
http://arxiv.org/abs/2501.11120
arxiv.org
http://arxiv.org/abs/2502.17424
arxiv.org
https://doi.org/10.1098/rstb.2018.0138
doi.org
https://link.springer.com/article/10.1007/s11023-012-9281-3
link.springer.com
https://nickbostrom.com/papers/porosity.pdf
nickbostrom.com
http://arxiv.org/abs/2211.03540
arxiv.org
http://arxiv.org/abs/2311.14125
arxiv.org
http://arxiv.org/abs/2505.03989
arxiv.org
http://arxiv.org/abs/2312.09390
arxiv.org
https://dl.acm.org/doi/10.1145/3490486.3538256
dl.acm.org
http://arxiv.org/abs/2311.08379
arxiv.org
https://www.alignmentforum.org/posts/F3j4xqpxjxgQD3xXh/ai-for-ai-safety
alignmentforum.org
https://www.alignmentforum.org/posts/nJcuj4rtuefeTRFHp/can-we-safely-automate-alignment-research
alignmentforum.org
https://www.lesswrong.com/posts/CPFfiRpWYCdyKcLCW/controlling-the-options-ais-can-pursue
lesswrong.com
https://www.lesswrong.com/posts/Kv7DRtEaQYjfyZ8Ld/giving-ais-safe-motivations
lesswrong.com
https://arxiv.org/abs/2507.16795
arxiv.org
https://arxiv.org/abs/2507.21509
arxiv.org
https://docs.google.com/document/d/1SUgGftOMKO4GVSBzOa3wMDcAhM4UrOGAjYVPnALxKY4/
docs.google.com
http://arxiv.org/abs/2406.10162
arxiv.org
http://arxiv.org/abs/2504.18530
arxiv.org
https://epoch.ai/epoch-after-hours/disagreements-on-agi-timelines
epoch.ai
https://www.lesswrong.com/posts/qw36iLrGyFn6mdwoa/making-deals-with-ais-a-tournament-experiment-with-a-bounty
lesswrong.com
https://www.alignmentforum.org/posts/uuikfACQBm4KJZp4w/being-honest-with-ais
alignmentforum.org
https://www.alignmentforum.org/posts/oLzoHA9ZtF2ygYgx4/notes-on-cooperating-with-unaligned-ais
alignmentforum.org
https://alignment.anthropic.com/2025/automated-researchers-sandbag/
alignment.anthropic.com
https://doi.org/10.1007/s11098-024-02102-0
doi.org
https://www.alignmentforum.org/posts/abmzgwfJA9acBoFEX/notes-on-countermeasures-for-exploration-hacking-aka
alignmentforum.org
http://arxiv.org/abs/2412.14093
arxiv.org
https://www.alignmentforum.org/posts/7C4KJot4aN8ieEDoz/will-alignment-faking-claude-accept-a-deal-to-reveal-its
alignmentforum.org
http://arxiv.org/abs/2405.19550
arxiv.org
https://www.alignmentforum.org/posts/kcKrE9mzEHrdqtDpE/the-case-for-ensuring-that-powerful-ais-are-controlled
alignmentforum.org
http://arxiv.org/abs/2312.06942
arxiv.org
http://arxiv.org/abs/2412.16339
arxiv.org
https://doi.org/10.1162/neco.1997.9.1.1
doi.org
https://alignment.anthropic.com/2025/reward-hacking-ooc/
alignment.anthropic.com
https://www.alignmentforum.org/posts/A9NxPTwbw6r6Awuwt/how-likely-is-deceptive-alignment
alignmentforum.org
http://arxiv.org/abs/1906.01820
arxiv.org
http://arxiv.org/abs/2103.10427
arxiv.org
http://arxiv.org/abs/1805.00899
arxiv.org
https://www.lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators
lesswrong.com
http://arxiv.org/abs/1912.02178
arxiv.org
https://www.alignmentforum.org/posts/HLJoJYi52mxgomujc/realistic-reward-hacking-induces-different-and-deeper-1
alignmentforum.org
https://www.jstor.org/stable/1914185
jstor.org
http://arxiv.org/abs/2407.04622
arxiv.org
https://docs.google.com/document/d/1u4wMYeuOjernzv2efW3AGQOIGTBj2fW8Qt-kuYdW0gA/
docs.google.com
https://ai-2027.com/research/ai-goals-forecast
ai-2027.com
http://arxiv.org/abs/2501.17315
arxiv.org
https://proceedings.mlr.press/v162/langosco22a.html
proceedings.mlr.press
http://arxiv.org/abs/2605.02087
arxiv.org
http://arxiv.org/abs/2411.00986
arxiv.org
http://arxiv.org/abs/2511.18397
arxiv.org
https://www.alignmentforum.org/posts/tkLSeGeemcabAmLkv/the-case-for-satiating-cheaply-satisfied-ai-preferences
alignmentforum.org
The Persona Selection Model: Why AI Assistants might Behave like Humans
alignment.anthropic.com
http://arxiv.org/abs/2503.10965
arxiv.org
https://arxiv.org/pdf/2508.00614
arxiv.org
http://arxiv.org/abs/1909.11522
arxiv.org
http://jmlr.org/papers/v22/20-676.html
jmlr.org
http://arxiv.org/abs/1905.11604
arxiv.org
https://openreview.net/forum?id=fh8EYKFKns
openreview.net
https://nostalgebraist.tumblr.com/post/785766737747574784/the-void
nostalgebraist.tumblr.com
https://openreview.net/forum?id=HJC2SzZCW
openreview.net
https://dl.acm.org/doi/10.5555/1566174.1566226
dl.acm.org
https://model-spec.openai.com/2025-12-18.html
model-spec.openai.com
https://www.lesswrong.com/posts/wHc2w6WuHev42d4n8/a-taxonomy-of-barriers-to-trading-with-early-misaligned-ais
lesswrong.com
http://arxiv.org/abs/2201.03544
arxiv.org
https://www.dwarkesh.com/p/give-ais-a-stake-in-the-future
dwarkesh.com
https://www.cambridge.org/core/elements/dutch-book-arguments/3A54DE6AB1006E159A85FC17922D5779
cambridge.org
https://www.jstor.org/stable/1913738
jstor.org
https://www.sciencedirect.com/science/article/pii/0167268182900087
sciencedirect.com
https://www.jstor.org/stable/2999450
jstor.org
https://proceedings.mlr.press/v97/rahaman19a.html
proceedings.mlr.press
https://papers.ssrn.com/abstract=4913167
papers.ssrn.com
http://arxiv.org/abs/2509.15541
arxiv.org
https://doi.org/10.1007/s43681-023-00379-1
doi.org
http://arxiv.org/abs/2210.01790
arxiv.org
https://www.alignmentforum.org/posts/TeTegzR8X5CuKgMc3/misalignment-and-strategic-underperformance-an-analysis-of
alignmentforum.org
https://intelligence.org/files/BasicAIDrives.pdf
intelligence.org
https://www.alignmentforum.org/posts/psqkwsKrKHCfkhrQx/making-deals-with-early-schemers
alignmentforum.org
https://doi.org/10.1007/s10670-020-00358-6
doi.org
http://arxiv.org/abs/2512.07810
arxiv.org
http://arxiv.org/abs/2508.17511
arxiv.org
https://www.journals.uchicago.edu/doi/full/10.1086/699256
journals.uchicago.edu
https://arxiv.org/abs/2601.10160v2
arxiv.org
https://www.alignmentforum.org/posts/LWfYjZgXHN5GYtYpH/intrinsic-power-seeking-ai-might-seek-power-for-power-s-sake
alignmentforum.org
https://www.alignmentforum.org/posts/yQSmcfN4kA7rATHGK/many-arguments-for-ai-x-risk-are-wrong
alignmentforum.org
http://arxiv.org/abs/2308.10248
arxiv.org
http://arxiv.org/abs/1805.08522
arxiv.org
http://arxiv.org/abs/2506.19823
arxiv.org
http://arxiv.org/abs/2406.07358
arxiv.org
https://www.alignmentforum.org/posts/jsmNCj9QKcfdg8fJk/an-introduction-to-ai-sandbagging
alignmentforum.org
https://www.lesswrong.com/posts/8wBN8cdNAv3c7vt6p/the-case-against-ai-control-research
lesswrong.com
https://doi.org/10.1093/pq/pqac056
doi.org
https://www.alignmentforum.org/posts/ocWqg2Pf2br4jMmKA/does-sgd-produce-deceptive-alignment
alignmentforum.org
https://www.lesswrong.com/posts/H67tq5sWPeHJxSqG8/all-about-concave-and-convex-agents
lesswrong.com
https://www.alignmentforum.org/posts/uMQ3cqWDPHhjtiesc/agi-ruin-a-list-of-lethalities
alignmentforum.org
https://drive.google.com/file/d/1XrJqTUDvwk3E6TPa5Yn8r3ZTwC2JQ-L1/view?usp=sharing
drive.google.com
https://onlinelibrary.wiley.com/doi/pdf/10.1111/nous.12398
onlinelibrary.wiley.com
https://onlinelibrary.wiley.com/doi/abs/10.1111/nous.12398
onlinelibrary.wiley.com
http://arxiv.org/abs/2310.01405
arxiv.org
Elsewhere on forethought.org (1)