Analyze shared links from AI Safety Fundamentals: Alignment

Another source it references often is Buzzsprout (47 links). The most cited link overall is a Other link, mentioned 94 times. Everything above comes straight from the public descriptions the creators wrote themselves. We don't add, remove, or assume anything.

Service

The table below shows each link, how many times AI Safety Fundamentals: Alignment has used it, and which other podcasts have cited the same link.

Link	#	Other Shows
https://aisafetyfundamentals.com/	94
https://bluedot.org/	83
https://type3.audio/	36
https://twitter.com/perrinjwalker	35
https://www.agisafetyfundamentals.com/	32
https://twitter.com/perrinjwalker%E2%80%9D%20target=	4	—
https://transformer-circuits.pub/2023/monosemantic-features/index.html	4
https://arxiv.org/abs/2212.03827	4
https://arxiv.org/abs/2205.10625	3	—
https://www.alignmentforum.org/posts/PJLABqQ962hZEqhdB/debate-update-obfuscated-arguments-problem	2	—
https://openai.com/research/learning-from-human-preferences	2
https://intelligence.org/2018/10/29/embedded-agents/	2	—
https://distill.pub/2017/feature-visualization/	2	—
https://aisafetyfundamentals.com/blog/alignment-careers-guide	2	—
https://arxiv.org/abs/1805.00899	2	—
https://www.governance.ai/post/computing-power-and-the-governance-of-ai	2	—
https://arxiv.org/abs/2209.00626	2	—
https://arxiv.org/pdf/2312.09390.pdf	2	—
https://drive.google.com/file/d/1QxMuScnYvyq-XmxYeqBRHKz7cZoOosHr/view	2	—
https://drive.google.com/file/d/1KewDov1taegTzrqJ4uurmJ2CJ0Y72EU3/view	2	—
https://www.anthropic.com/news/evaluating-ai-systems	2	—
https://aisafetyfundamentals.com/blog/scalable-oversight-intro/	2	—
https://www.alignmentforum.org/posts/h9DesGT3WT9u2k7Hr/the-easy-goal-inference-problem-is-still-hard	2	—
https://bounded-regret.ghost.io/future-ml-systems-will-be-qualitatively-different/	2	—
https://medium.com/@richardcngo/visualizing-the-deep-learning-revolution-722098eb9c5	2	—
https://www.alignmentforum.org/posts/n3LAgnHg6ashQK3fF/takeaways-from-our-robust-injury-classifier-project-redwood	2	—
https://arxiv.org/abs/2211.03540	2
https://arxiv.org/abs/2111.09259	2
https://www.neelnanda.io/blog/become-a-person-who-actually-does-things	2	—
https://distill.pub/2020/circuits/zoom-in/	2
https://forum.effectivealtruism.org/posts/jfHPBbYFzCrbdEXXd/how-to-succeed-as-an-early-stage-researcher-the-lean-startup#Conclusion	2	—
https://www.alignmentforum.org/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion	2	—
https://arxiv.org/abs/2110.03605	2	—
https://www.lesswrong.com/posts/XvN2QQpKTuEzgkZHY/being-the-pareto-best-in-the-world	2	—
https://deepmindsafetyresearch.medium.com/progress-on-causal-influence-diagrams-a7a32180b0d1	2	—
https://arxiv.org/pdf/2211.00593.pdf	2	—
https://medium.com/machine-learning-for-humans/supervised-learning-740383a2feab	2	—
https://www.gov.uk/government/publications/emerging-processes-for-frontier-ai-safety/emerging-processes-for-frontier-ai-safety	2	—
https://www.deepmind.com/blog/specification-gaming-the-flip-side-of-ai-ingenuity	2	—
https://arbital.com/p/logical_dt/?l=5d6	2	—
https://www.getonbrd.com/blog/public-by-default-how-we-manage-information-visibility-at-get-on-board	2	—
https://www.lesswrong.com/posts/kDjKF2yFhFEWe4hgC/announcing-the-lesswrong-curated-podcast	2	—
https://www.cold-takes.com/why-ai-alignment-could-be-hard-with-modern-deep-learning/	2
https://www.alignmentforum.org/s/p947tK8CoBbdpPtyK/p/KMocAf9jnAKc2jXri	2	—
https://intelligence.org/2015/07/24/four-background-claims/	2	—
https://www.alignmentforum.org/posts/qE73pqxAZmeACsAdF/a-short-introduction-to-machine-learning	2	—
https://www.lesswrong.com/posts/yTvBSFrXhZfL8vr5a/worst-case-thinking-in-ai-alignment	2	—
https://www.scotthyoung.com/blog/2019/01/24/how-to-get-feedback/	2	—
https://deepmindsafetyresearch.medium.com/goal-misgeneralisation-why-correct-specifications-arent-enough-for-correct-goals-cf96ebc60924	2	—
https://arxiv.org/abs/2108.07258	2

About Methodology Contact Support me Privacy Policy Legal Notice