pod.link/1611393245
pod.link copied!
The Nonlinear Library: Alignment Forum
The Nonlinear Library: Alignment Forum
The Nonlinear Fund

The Nonlinear Library allows you to easily listen to top EA and rationalist content on your podcast player. We use text-to-speech software... more

Listen now on

Apple Podcasts
Spotify
Google Podcasts
Overcast
Podcast Addict
Pocket Casts
Castbox
Stitcher
Podbean
iHeartRadio
Player FM
Podcast Republic
Castro
RadioPublic
RSS

Episodes

AF - Simple probes can catch sleeper agents by Monte MacDiarmid

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the... more

23 Apr 2024 · 2 minutes
AF - Dequantifying first-order theories by Jessica Taylor

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the... more

23 Apr 2024 · 13 minutes
AF - Time complexity for deterministic string machines by alcatal

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the... more

22 Apr 2024 · 36 minutes
AF - Inducing Unprompted Misalignment in LLMs by Sam Svenningsen

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the... more

19 Apr 2024 · 35 minutes
AF - Progress Update #1 from the GDM Mech Interp Team: Full Update by Neel Nanda

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the... more

19 Apr 2024 · 1 hour, 19 minutes
AF - Progress Update #1 from the GDM Mech Interp Team: Summary by Neel Nanda

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the... more

19 Apr 2024 · 5 minutes
AF - Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight by Sam Marks

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the... more

18 Apr 2024 · 21 minutes
AF - LLM Evaluators Recognize and Favor Their Own Generations by Arjun Panickssery

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the... more

17 Apr 2024 · 5 minutes
AF - Transformers Represent Belief State Geometry in their Residual Stream by Adam Shai

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the... more

16 Apr 2024 · 20 minutes
AF - Speedrun ruiner research idea by Luke H Miles

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the... more

13 Apr 2024 · 2 minutes
© 2023 pod.link
TermsPrivacyTwitterClaim PodcastClear CacheHelp
The Nonlinear Library: Alignment Forum
AF - Simple probes can catch sleeper agents by Monte MacDiarmid
The Nonlinear Library: Alignment Forum