Mechanistic estimation for expectations of random products

·ARC··

We have developed some relatively general methods for mechanistic estimation competitive with sampling by studying problems that are expressible as expectations of random products. This includes several different estimation problems, such as random halfspace intersections, random #3-SAT and random permanents. In this post, we will give a high-level introduction to these methods before sharing some more detailed notes. This is intended as an interim technical update and will be relatively light o...

Read full article →

Related Articles

Sequent: scale and automation for higher confidence in alignment
Geoffrey Irving · Alignment Forum · 25d ago
My research: a computational cognitive neuroscience perspective on alignment
Seth Herd · Alignment Forum · 1mo ago
A Pipeline for Generating Synthetic Sabotage Trajectories to Red-Team Monitors
Myles H · LessWrong · 1mo ago
Announcing the ARC White-Box Estimation Challenge
Jacob_Hilton · Alignment Forum · 1mo ago
The Case for Evaluating Model Behaviors
jsteinhardt · Alignment Forum · 1mo ago