Redwood Research blog

Redwood Research blog

Home
Podcast
Reading List
Archive
About
Most Popular
View all

Recent posts

View all
How do we (more) safely defer to AIs?
How can we make AIs aligned and well-elicited on extremely hard to check open ended tasks?
 • Ryan Greenblatt and Julian Stastny
Distinguish between inference scaling and "larger tasks use more compute"
Most recent progress probably isn't from unsustainable inference scaling
 • Ryan Greenblatt
Fitness-Seekers: Generalizing the Reward-Seeking Threat Model
If you think reward-seekers are plausible, you should also think “fitness-seekers” are plausible. But their risks aren’t the same.
 • Alex Mallen
The inaugural Redwood Research podcast
With Buck Shlegeris and Ryan Greenblatt
 • Buck Shlegeris
3:52:01
Recent LLMs can do 2-hop and 3-hop latent (no CoT) reasoning on natural facts
Recent AIs are much better at chaining together knowledge in a single forward pass
 • Ryan Greenblatt
Measuring no CoT math time horizon (single forward pass)
Opus 4.5 has around a 3.5 minute 50%-reliablity time horizon
 • Ryan Greenblatt
The latest from
Buck Shlegeris
Announcing ControlConf 2026
User's avatar
Alex Mallen
Will reward-seekers respond to distant incentives?
User's avatar
Ryan Greenblatt
How do we (more) safely defer to AIs?
User's avatar
Julian Stastny
How do we (more) safely defer to AIs?
User's avatar
Josh Clymer
Will AI systems drift into misalignment?
User's avatar
Vivek Hebbar
Recent Redwood Research project proposals
User's avatar
Redwood Research blog
Redwood Research blog
We research catastrophic AI risks and techniques that could be used to mitigate them.
Recommendations
AI Futures Project
AI Futures Project
Daniel Kokotajlo
The Power Law
The Power Law
Peter Wildeford
ForeWord
ForeWord
Forethought
© 2026 Buck Shlegeris · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture