Research Meeting: Computational Feasibility of Artificial Human-Level Intelligence

October 29, 2024 - 4:00 pm to 5:30 pm
Speaker/s: 

Eran Malach, Harvard University

Organizer: 

Abstract: Modern machine learning models, in particular large language models, are approaching and even surpassing human-level performance at various benchmarks. In this talk, I will discuss the possibilities and barriers towards achieving human-level intelligence from a computational learning theory perspective. Specifically, I will talk about how auto-regressive next-token predictors can learn to solve computationally complex tasks. Additionally, I will discuss how generative models can “transcend” their training data, outperforming the experts that generate their data, with specific focus on learning to play chess from game transcripts.

Details

MIT Building 46
Date: 
October 29, 2024
Time: 
4:00 pm to 5:30 pm
Venue: 
Room 45-792