Sign up to save your podcasts
Or
Share “Recent Redwood Research project proposals” by ryan_greenblatt, Buck, Julian Stastny, joshc, Alex Mallen, Adam Kaufman, Tyler Tracy, Aryan Bhatt, Joey Yudelson
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
“Recent Redwood Research project proposals” by ryan_greenblatt, Buck, Julian Stastny, joshc, Alex Mallen, Adam Kaufman, Tyler Tracy, Aryan Bhatt, Joey Yudelson
Previously, we've shared a few higher-effort project proposals relating to AI control in particular. In this post, we'll share a whole host of less polished project proposals. All of these projects excite at least one Redwood researcher, and high-quality research on any of these problems seems pretty valuable. They differ widely in scope, area, and difficulty.
Control
These projects are all related to the field of AI Control. Many of them are extensions of Redwood's previous work in this area.
Basic open questions in control
---
Outline:
(00:36) Control
(00:47) Basic open questions in control
(01:46) Monitoring protocols
(02:49) Untrusted monitoring and collusion
(03:31) Elicitation, sandbagging, and diffuse threats (e.g. research sabotage)
(04:05) Synthetic information and inputs
(04:38) Training-time alignment methods
(04:42) Science of (mis-)alignment
(05:23) Alignment / training schemes
(05:53) RL and Reward Hacking
(06:20) Better understanding and interpretability
(07:43) Other
---
First published:
July 14th, 2025
Source:
https://www.lesswrong.com/posts/RRxhzshdpneyTzKfq/recent-redwood-research-project-proposals
---
Narrated by TYPE III AUDIO.
View all episodes
By LessWrongPreviously, we've shared a few higher-effort project proposals relating to AI control in particular. In this post, we'll share a whole host of less polished project proposals. All of these projects excite at least one Redwood researcher, and high-quality research on any of these problems seems pretty valuable. They differ widely in scope, area, and difficulty.
Control
These projects are all related to the field of AI Control. Many of them are extensions of Redwood's previous work in this area.
Basic open questions in control
---
Outline:
(00:36) Control
(00:47) Basic open questions in control
(01:46) Monitoring protocols
(02:49) Untrusted monitoring and collusion
(03:31) Elicitation, sandbagging, and diffuse threats (e.g. research sabotage)
(04:05) Synthetic information and inputs
(04:38) Training-time alignment methods
(04:42) Science of (mis-)alignment
(05:23) Alignment / training schemes
(05:53) RL and Reward Hacking
(06:20) Better understanding and interpretability
(07:43) Other
---
First published:
July 14th, 2025
Source:
https://www.lesswrong.com/posts/RRxhzshdpneyTzKfq/recent-redwood-research-project-proposals
---
Narrated by TYPE III AUDIO.
More shows like LessWrong (30+ Karma)
View all
Making Sense with Sam Harris
26,469 Listeners
Conversations with Tyler
2,395 Listeners
The Peter Attia Drive
7,928 Listeners
Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas
4,142 Listeners
ManifoldOne
89 Listeners
Your Undivided Attention
1,472 Listeners
All-In with Chamath, Jason, Sacks & Friedberg
9,207 Listeners
Machine Learning Street Talk (MLST)
88 Listeners
Dwarkesh Podcast
417 Listeners
Hard Fork
5,448 Listeners
The Ezra Klein Show
15,237 Listeners
Moonshots with Peter Diamandis
481 Listeners
No Priors: Artificial Intelligence | Technology | Startups
121 Listeners
Latent Space: The AI Engineer Podcast
75 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
461 Listeners