The AI Alignment Forum

FEBRUARY 28, 2025

Finally, in the last post, I will also provide some resources for anyone who wants to contribute to this (or similar) research, in the form of both open problems and some thoughts on how these problems could be approached. We should only trust a reward learning method that is at least reasonably robust to such errors.

Research 40

Research Learning Method Policy 40

The AI Alignment Forum

FEBRUARY 28, 2025

To me, the main takeaway from this paper is that we should be careful with the assumption that the basic RL setting really captures everything that we intuitively consider to be part of the problem domain of sequential decision-making. This paper is discussed in more detail in this post. Alternatively, see the main paper.

Learning 40

Learning Discussion Classes Policy 40

The AI Alignment Forum

FEBRUARY 7, 2025

This guide provides an opinionated overview of recent work and open problems across areas like adversarial testing, model transparency, and theoretical approaches to AI alignment. Motivation: Two lines of recent work have looked for undesirable behaviors in LLMs, approaching the problem from two different angles: Andriushchenko et al.

Research 52

Research Fund Open Technique 52

DataRobot

APRIL 21, 2022

They are used for different applications, but nonetheless they suggest that the development in infrastructure (access to GPUs and TPUs for computing) and the development in deep learning theory has led to very large models. For us, we believe in using efficiency metrics in machine learning software.

Green 145

Green Environment Metrics Measure 145

Google Research AI blog

NOVEMBER 28, 2022

A Workshop for Algorithmic Efficiency in Practical Neural Network Training Workshop Organizers include: Zachary Nado , George Dahl , Naman Agarwal , Aakanksha Chowdhery Invited Speakers include: Aakanksha Chowdhery , Priya Goyal Human in the Loop Learning (HiLL) Workshop Organizers include: Fisher Yu, Vittorio Ferrari Invited Speakers include: Dorsa (..)

Google 52

Google Language Tutorial Offline 52

The AI Alignment Forum

MARCH 28, 2025

And the way you said it just then, it sounded more like the first one: heres a new nice metric of how good your mechanistic explanation is. You could imagine saying, Oh, we figured out that the difficulties in finding It was still kind of hard and our lives would be easier if we solved sub-problems, X, Y and Z.

Model 52

Model Network Training Train 52