Large language models (LLMs) may not equitably represent diverse global perspectives on societal issues. In this paper, we develop a quantitative framework to evaluate whose opinions model-generated responses are more similar to. We first build a dataset, GlobalOpinionQA, comprised of questions and answers from cross-national surveys designed to capture diverse opinions on global issues across different countries. Next, we define a metric that quantifies the similarity between LLM-generated survey responses and human responses, conditioned on country. With our framework, we run three experiments on an LLM trained to be helpful, honest, and harmless with Constitutional AI. By default, LLM responses tend to be more similar to the opinions of certain populations, such as those from the USA, and some European and South American countries, highlighting the potential for biases. When we prompt the model to consider a particular country's perspective, responses shift to be more similar to the opinions of the prompted populations, but can reflect harmful cultural stereotypes. When we translate GlobalOpinionQA questions to a target language, the model's responses do not necessarily become the most similar to the opinions of speakers of those languages. We release our dataset for others to use and build on. Our data is at https://huggingface.co/datasets/Anthropic/llm_global_opinions. We also provide an interactive visualization at https://llmglobalvalues.anthropic.com.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. BRUSSELS (AP) -- European Union lawmakers approved Wednesday a major revamp of the bloc's migration laws, hoping to end years of division over how to manage the entry of thousands of people without authorization and deprive the far right of a vote-winning campaign issue ahead of June elections. In a series of 10 votes, members of the European Parliament endorsed the regulations and policies that make up the Pact on Migration and Asylum. The reforms address the thorny issue of who should take responsibility for migrants when they arrive and whether other EU countries should be obliged to help. The proceedings were briefly interrupted by a small but noisy group of demonstrators in the public gallery who wore shirts marked "this pact kills" and shouted "vote no!" European Commissioner for Home Affairs Ylva Johansson, is embraced after Members of the European Parliament participated in a series of votes during a plenary session at the European Parliament in Brussels, Wednesday, April 10, 2024.

Frank Kendall, the secretary of the Air Force, told the U.S. Senate Committee on Appropriations he will get to fly in an AI-flown plane later this year. Air Force Secretary Frank Kendall told members of the U.S. Senate on Tuesday that he plans to ride in the cockpit of an aircraft operated by artificial intelligence. An F-16 169th Fighter Wing jet is seen in 2023. FLIGHT RISKS: Air Force Secretary Frank Kendall told members of the U.S. Senate on Tuesday that he plans to ride in the cockpit of an aircraft operated by artificial intelligence to experience the technology of the military branch's future fleet. 'KEEPING BEAUTY REAL': As experts predict that 90% of online content could be generated by artificial intelligence by the year 2025, a major beauty brand is taking a stand against the use of AI in advertising.

Recently, Donald Trump fans in Florida and Michigan have been auto-generating and spreading around faked "pictures" of Trump surrounded by crowds of Black supporters--and earning significant traction for doing so. Coming at a time when President Joe Biden is worried about losing the Black voters who came out for his 2020 election, the Trump images have become a whole new subgenre of A.I. sludge. And no one in any position of power appears to know what to do about it. Last month, BBC Panorama reported on the proliferation of these deceitful likenesses. The first example displayed Trump at a Christmas party with his arm around a couple of Black women, one of whom is seen wearing a Pen & Pixel–style tank; another shows him sitting on a house porch with six young Black men, smiling with his hands clasped.

"AI has the disruptive potential of changing our economy, our political system, and our day-to-day lives. We must balance the immense potential of AI with the crucial need for ethical guidelines and protections." said Congressman Schiff in a statement. He added that the bill "champions innovation while safeguarding the rights and contributions of creators, ensuring they are aware when their work contributes to AI training datasets. This is about respecting creativity in the age of AI and marrying technological progress with fairness." Organizations such as the Recording Industry Association of America (RIAA), SAG-AFTRA and WGA have shown support for the bill. They would also have to provide the same information retroactively for any existing tools and make updates if they considerably altered datasets.

In their work Resource Democratization: Is Compute the Binding Constraint on AI Research?, presented at AAAI 2024, Rebecca Gelles, Veronica Kinoshita, Micah Musser and James Dunham investigate researchers' access to compute and the impact this has on their work. In this interview, Rebecca and Ronnie tell us about what inspired their study, their methodology and some of their main findings. We wanted to engage directly with AI researchers to understand their resource constraints when deciding what types of research to dedicate their time to. We also wanted to dig deeper and try to understand how resource constraints play out across the AI research community – particularly looking at divides between industry and academia, a popular topic of discussions about AI resource constraints. The reason we were interested in this question is that there's a lot of discourse, particularly from the policy community, about the democratization of AI, addressing inequities in the field, and the fear that progress in AI may be held back by resource constraints.

On the eve of New Hampshire's primary election, a flood of robocalls exhorted Democratic voters to sit out a write-in campaign supporting President Joe Biden during the state's presidential primary. An AI-generated voice on the line matched the uncanny cadence and signature catchphrase-- ("malarkey!")--characteristic to Biden. From that call to fake creations envisioning a cascade of calamities under Biden's watch to AI deepfakes of a Slovakian candidate for country leader pondering vote rigging and raising beer prices, AI is making its mark on elections worldwide. Against this backdrop, governments and several tech companies are taking some steps to mitigate risks--European lawmakers just approved a watershed law, and as recently as February tech companies signed a pledge at the Munich Security Conference. But much more needs to be done to protect American democracy.

Many US election deniers have spent the past three years inundating local election officials with paperwork and filing thousands of Freedom of Information Act requests in order to surface supposed instances of fraud. "I've had election officials telling me that in an office where there's one or two workers, they literally were satisfying public records requests from 9 to 5 every day, and then it's 5 o'clock and they would shift to their normal election duties," says Tammy Patrick, CEO of the National Association of Election Officials. In Washington state, elections officials were receiving so many FOIA requests following the 2020 presidential elections about the state's voter registration database that the legislature had to change the law, rerouting these requests to the Secretary of State's office to relieve the burden on local elections workers. "Our county auditors came in and testified as to how much time having to respond to public records requests was taking," says democratic state senator Patty Kederer, who cosponsored the legislation. "It can cost a lot of money to process those requests. And some of these smaller counties do not have the manpower to handle them. You could easily overwhelm some of our smaller counties."

So I was inspired after talking to Angela Huyue Zhang, a law professor in Hong Kong who's coming to teach at the University of Southern California this fall, about her new book on interpreting the logic and patterns behind China's tech regulations. We talked about how the Chinese government almost always swings back and forth between regulating tech too much and not enough, how local governments have gone to great lengths to protect local tech companies, and why AI companies in China are receiving more government goodwill than other sectors today. To learn more about Zhang's fascinating interpretation of the tech regulations in China, read my story published today. In this newsletter, I want to show you a particularly interesting part of the conversation we had, where Zhang expanded on how market overreactions to Chinese tech policies have become an integral part of the tech regulator's toolbox today. The capital markets, perpetually betting on whether tech companies are going to fare better or worse, are always looking for policy signals on whether China is going to start a new crackdown on certain technologies. As a result, they often overreact to every move by the Chinese government.

"It's very easy to see when you've got the memory right, because there is a very visceral reaction," says Pau Garcia, founder of Domestic Data Streamers. Dozens of people have now had their memories turned into images in this way via Synthetic Memories, a project run by Domestic Data Streamers. The studio uses generative image models, such as OpenAI's DALL-E, to bring people's memories to life. Since 2022, the studio, which has received funding from the UN and Google, has been working with immigrant and refugee communities around the world to create images of scenes that have never been photographed, or to re-create photos that were lost when families left their previous homes. Now Domestic Data Streamers is taking over a building next to the Barcelona Design Museum to record people's memories of the city using synthetic images.