corpus.blog
56,966 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a08c6e-03f4-7052-9e6d-ea9ea4553771

An operationalization of opaque serial depth

AI Alignment Forum · published 10 September 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
46
Words captured
15,414

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://arxiv.org/pdf/2507.11473
arxiv.org
https://cdn.prod.website-files.com/663bd486c5e4c81588db7a1d/6a0ed93f9b4a6a65994235d8_Loss_of_Oversight%20(7
cdn.prod.website-files.com
https://www.redwoodresearch.org/blog/proposal-for-tracking-architecture-on-monitorability
redwoodresearch.org
https://arxiv.org/abs/2603.09786
arxiv.org
https://arxiv.org/abs/2604.22709
arxiv.org
https://arxiv.org/abs/2412.06769
arxiv.org
https://arxiv.org/abs/2608.08888
arxiv.org
https://arxiv.org/abs/2505.15778
arxiv.org
https://arxiv.org/pdf/2608.08888
arxiv.org
https://arxiv.org/pdf/2603.09786
arxiv.org
https://transformer-circuits.pub/2026/nla/
transformer-circuits.pub
https://arxiv.org/abs/2512.23675
arxiv.org
https://arxiv.org/abs/2502.05171
arxiv.org
https://arxiv.org/pdf/2502.05171
arxiv.org
https://deploymentsafety.openai.com/gpt-6-astra/evaluations-with-challenging-prompts
deploymentsafety.openai.com
https://arxiv.org/pdf/2405.14838
arxiv.org
https://arxiv.org/abs/1905.11006
arxiv.org
https://arxiv.org/abs/1902.03249
arxiv.org
https://arxiv.org/pdf/2502.09992
arxiv.org
https://arxiv.org/abs/2508.15487
arxiv.org
https://deepmind.google/models/gemma/diffusiongemma/
deepmind.google
https://arxiv.org/abs/2312.00752
arxiv.org
https://arxiv.org/abs/2406.06484
arxiv.org
https://arxiv.org/pdf/2412.06769
arxiv.org
https://arxiv.org/pdf/2604.22709
arxiv.org
https://arxiv.org/abs/2505.14827
arxiv.org
https://arxiv.org/abs/2508.03440
arxiv.org
https://arxiv.org/pdf/2305.18619
arxiv.org
https://arxiv.org/abs/2510.01329
arxiv.org
https://arxiv.org/pdf/2606.20560
arxiv.org
https://arxiv.org/pdf/1709.07432
arxiv.org
https://arxiv.org/pdf/2512.23675
arxiv.org
https://arxiv.org/pdf/2602.07470
arxiv.org
https://cdn.sanity.io/files/4zrzovbb/website/7624816413e9b4d2e3ba620c5a5e091b98b190a5.pdf
cdn.sanity.io
https://arxiv.org/abs/2606.07157
arxiv.org
https://blog.redwoodresearch.org/p/ai-catastrophes-and-rogue-deployments
blog.redwoodresearch.org
AI agent collaboration Read at the source ↗
metr.org
https://deploymentsafety.openai.com/gpt-6-astra/model-data-and-training
deploymentsafety.openai.com
https://arxiv.org/html/2511.11584v1
arxiv.org
https://github.com/google-deepmind/serial_depth
github.com
https://arxiv.org/abs/2203.15556
arxiv.org
https://epoch.ai/trends
epoch.ai
https://en.wikipedia.org/wiki/Sinkhorn%27s_theorem
en.wikipedia.org
https://x.com/merettm/status/2095023204993490967
x.com
https://www.theinformation.com/articles/secret-technique-behind-openais-astra-model-sparks-security-concerns?rc=4s6b2t
theinformation.com
https://arxiv.org/abs/2601.05732v1
arxiv.org