The AI Alignment Forum

FEBRUARY 28, 2025

Concretely, this research agenda involves answering questions such as: What is the right method for expressing goals and instructions to AI systems? Similarly, a complete answer to (3) would be a (pseudo)metric d on the space of all reward functions which quantifies their similarity.

Research 40

Research Learning Method Policy 40

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

The third and final class of tasks I look at in this paper is a new category of objectives that I refer to as modal objectives, where the agent is given an instruction expressed not just in terms of what does happen along a given trajectory, but also in terms of what could happen. This paper is discussed in more detail in this post.

Learning 40

Learning Discussion Classes Policy 40

The AI Alignment Forum

FEBRUARY 7, 2025

display inputs on which LLMs take undesirable/misaligned actions without being instructed to do so. 3.6) ) than we do inputs that include instructions to do some harmful task (as in Andriushchenko et al. Kumar et al. , OpenAI , Yuan et al. Jrviniemi and Hubinger ( 4) , and Meinke et al. Jrviniemi and Hubinger ( 4) , Meinke et al.

Research 52

Research Fund Open Technique 52