The AI Alignment Forum

FEBRUARY 20, 2025

Published on February 20, 2025 11:54 PM GMT TLDR: We made substantial progress in 2024: We published a series of papers that verify key predictions of Singular Learning Theory (SLT) [ 1 , 2 , 3 , 4 , 5 , 6 ]. We are now pursuing direct impact in three main directions: Near-term Applications. Interpretability ("Reading").

Technique 52

Technique Sample Structure Train 52

Google Research AI blog

APRIL 30, 2023

If you’re registered for ICLR 2023, we hope you’ll visit the Google booth to learn more about the exciting work we’re doing across topics spanning representation and reinforcement learning, theory and optimization, social impact, safety and privacy, and applications from generative AI to speech and robotics.

Google 105

Google Language Model Jing 105

Stanford AI Lab Blog

DECEMBER 6, 2021

Kochenderfer Contact : philhc@stanford.edu Links: Paper Keywords : deep learning or neural networks, sparsity and feature selection, variational inference, (application) natural language and text processing Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss Authors : Jeff Z.

Contact 40

Contact Learning Theory Authoring Offline 40

The AI Alignment Forum

FEBRUARY 28, 2025

Progress on this research agenda therefore seems likely to be useful in a fairly broad range of scenarios, and applicable to a fairly broad range of AI systems (in contrast to research that is closely tied to specific alignment strategies, specific types of AI systems, or very specific assumptions).

Research 40

Research Learning Method Policy 40

The AI Alignment Forum

FEBRUARY 28, 2025

The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret In this paper , we look at what happens when a learnt reward function is optimised. This means that it essentially makes the analysis in this paper more realistic, and more closely applicable to humans.

Learning 40

Learning Discussion Classes Policy 40

The AI Alignment Forum

FEBRUARY 7, 2025

Applications ( here ) start with a simple 300 word expression of interest and are open until April 15, 2025. We have plans to fund $40M in grants and have available funding for substantially more depending on application quality. Inter-model messages: Some applications of LLMs involve multiple models working together.

Research 52

Research Fund Open Technique 52

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

The other part is the really exciting part because it has applications to what other people are doing in mech interp, which is that if you were just doing this epsilon-ball propagation, youd still have to do it for every data point separately, which saves you nothing because you still need to propagate every data point through the network.

Model 52

Model Network Train Training 52