Comparison, Learning Theory and Metrics

Research directions Open Phil wants to fund in technical AI safety

The AI Alignment Forum

FEBRUARY 7, 2025

We prefer this definition of success at unlearning over the less conservative metrics like in Lynch et al because we think this definition more clearly distinguishes unlearning from safety training/robustness. Wed also be keen to see comparisons with supervised finetuning, RLHF, and adversarial training where appropriate.

Research

Research Fund Open Technique

Moving from Red AI to Green AI, Part 1: How to Save the Environment and Reduce Your Hardware Costs

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. To illustrate the energy needed in deep learning, let’s make a comparison.

Green

Green Environment Metrics Measure

Nonprofit Technology

Research directions Open Phil wants to fund in technical AI safety

Moving from Red AI to Green AI, Part 1: How to Save the Environment and Reduce Your Hardware Costs

Webinars

Stay Connected