Considerations Influencing Offense-Defense Dynamics From Artificial Intelligence

no code implementations • 5 Dec 2024 • Giulio Corsi, Kyle Kilian, Richard Mallah

The rapid advancement of artificial intelligence (AI) technologies presents profound challenges to societal safety.

Decision Making

Auditing Google's Search Algorithm: Measuring News Diversity Across Brazil, the UK, and the US

no code implementations • 31 Oct 2024 • Raphael Hernandes, Giulio Corsi

This study examines the influence of Google's search algorithm on news diversity by analyzing search results in Brazil, the UK, and the US.

Diversity

Artificial Intelligence in Brazilian News: A Mixed-Methods Analysis

no code implementations • 22 Oct 2024 • Raphael Hernandes, Giulio Corsi

The current surge in Artificial Intelligence (AI) interest, reflected in heightened media coverage since 2009, has sparked significant debate on AI's implications for privacy, social justice, workers' rights, and democracy.

named-entity-recognition Named Entity Recognition

LLMs left, right, and center: Assessing GPT's capabilities to label political bias from web domains

no code implementations • 19 Jul 2024 • Raphael Hernandes, Giulio Corsi

This research investigates whether OpenAI's GPT-4, a state-of-the-art large language model, can accurately classify the political bias of news sources based solely on their URLs.

Language Modelling Large Language Model

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

1 code implementation • 15 Apr 2024 • Usman Anwar, Abulhair Saparov, Javier Rando, Daniel Paleka, Miles Turpin, Peter Hase, Ekdeep Singh Lubana, Erik Jenner, Stephen Casper, Oliver Sourbut, Benjamin L. Edelman, Zhaowei Zhang, Mario Günther, Anton Korinek, Jose Hernandez-Orallo, Lewis Hammond, Eric Bigelow, Alexander Pan, Lauro Langosco, Tomasz Korbak, Heidi Zhang, Ruiqi Zhong, Seán Ó hÉigeartaigh, Gabriel Recchia, Giulio Corsi, Alan Chan, Markus Anderljung, Lilian Edwards, Aleksandar Petrov, Christian Schroeder de Witt, Sumeet Ramesh Motwan, Yoshua Bengio, Danqi Chen, Philip H. S. Torr, Samuel Albanie, Tegan Maharaj, Jakob Foerster, Florian Tramer, He He, Atoosa Kasirzadeh, Yejin Choi, David Krueger

This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs).