Language Learning Theory Metrics 
The AI Alignment Forum
FEBRUARY 28, 2025
Some relevant criteria for evaluating a specification language include: How expressive is the language? What is the right way to quantify the differences and similarities between different goal specifications in a given specification language? Are there things it cannot express? How intuitive is it for humans to work with?
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.
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
The AI Alignment Forum
FEBRUARY 28, 2025
Goodhart's Law in Reinforcement Learning As you probably know, "Goodhart's Law" is an informal principle which says that "if a proxy is used as a target, it will cease to be a good proxy". This paper is also discussed in this post (Paper 4). For details, see the full paper. This paper is discussed in more detail in this post.
The AI Alignment Forum
FEBRUARY 7, 2025
In either of these settings, theres a chance that the LLMs will write messages that encode meaning beyond the natural language definitions of the words used. Externalizing reasoning: It could be safer to have much smaller language models which put more reasoning into natural language. and Mathew et al. Roger and Greenblatt ).
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.
Google Research AI blog
NOVEMBER 28, 2022
Platt , Fernando Pereira , Dale Schuurmans Keynote Speakers The Data-Centric Era: How ML is Becoming an Experimental Science Isabelle Guyon The Forward-Forward Algorithm for Training Deep Neural Networks Geoffrey Hinton Outstanding Paper Award Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding Chitwan Saharia , William Chan (..)
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. 00:26:47): And so what this gives us is an interaction metric where we can measure how bad this hypothesis is. But I dont know, it feels kind of surprising for that to be the explanation.
Expert insights. Personalized for you.
40 
Let's personalize your content