Picture for Jon Kleinberg

Jon Kleinberg

The Backfiring Effect of Weak AI Safety Regulation

Add code
Mar 26, 2025
Viaarxiv icon

AI-Assisted Decision Making with Human Learning

Add code
Feb 18, 2025
Viaarxiv icon

Sparse Autoencoders for Hypothesis Generation

Add code
Feb 05, 2025
Figure 1 for Sparse Autoencoders for Hypothesis Generation
Figure 2 for Sparse Autoencoders for Hypothesis Generation
Figure 3 for Sparse Autoencoders for Hypothesis Generation
Figure 4 for Sparse Autoencoders for Hypothesis Generation
Viaarxiv icon

A No Free Lunch Theorem for Human-AI Collaboration

Add code
Nov 21, 2024
Viaarxiv icon

Maia-2: A Unified Model for Human-AI Alignment in Chess

Add code
Sep 30, 2024
Viaarxiv icon

Evaluating the World Model Implicit in a Generative Model

Add code
Jun 06, 2024
Viaarxiv icon

How Random is Random? Evaluating the Randomness and Humaness of LLMs' Coin Flips

Add code
May 31, 2024
Viaarxiv icon

Designing Skill-Compatible AI: Methodologies and Frameworks in Chess

Add code
May 08, 2024
Viaarxiv icon

Language Generation in the Limit

Add code
Apr 10, 2024
Viaarxiv icon

Microstructures and Accuracy of Graph Recall by Large Language Models

Add code
Feb 20, 2024
Figure 1 for Microstructures and Accuracy of Graph Recall by Large Language Models
Figure 2 for Microstructures and Accuracy of Graph Recall by Large Language Models
Figure 3 for Microstructures and Accuracy of Graph Recall by Large Language Models
Figure 4 for Microstructures and Accuracy of Graph Recall by Large Language Models
Viaarxiv icon