A central architectural question for both biological and artificial intelligence is whether judgment relies on specialized modules or a unified, domain-general resource. While the discovery of decodable neural representations for distinct concepts in Large Language Models (LLMs) has suggested a modular architecture, whether these representations are truly independent systems remains an open question. Here we provide evidence for a convergent architecture for evaluative judgment. Across a range of LLMs, we find that diverse evaluative judgments are computed along a dominant dimension, which we term the Valence-Assent Axis (VAA). This axis jointly encodes subjective valence ("what is good") and the model's assent to factual claims ("what is true"). Through direct interventions, we demonstrate this axis drives a critical mechanism, which is identified as the subordination of reasoning: the VAA functions as a control signal that steers the generative process to construct a rationale consistent with its evaluative state, even at the cost of factual accuracy. Our discovery offers a mechanistic account for response bias and hallucination, revealing how an architecture that promotes coherent judgment can systematically undermine faithful reasoning.

I was struck by her pessimism, which she told me was shared by friends from California to Georgia to New Hampshire. In an already fragile world, one increasingly beset by climate change and the breakdown of the international order, AI looms in the background, threatening young people's ability to secure a prosperous future. Just a few days before our drive, OpenAI CEO Sam Altman was telling the US Federal Reserve's board of governors that AI agents will leave entire job categories "just like totally, totally gone." Anthropic CEO Dario Amodei told Axios he believes AI will wipe out half of all entry-level white-collar jobs in the next five years. Amazon CEO Andy Jassy said the company will eliminate jobs in favor of AI agents in the coming years. Shopify CEO Tobi Lütke told staff they had to prove that new roles couldn't be done by AI before making a hire.

Current efforts in AI safety prioritize filtering harmful content, preventing manipulation of human behavior, and eliminating existential risks in cybersecurity or biosecurity. While pressing, this narrow focus overlooks critical human-centric considerations that shape the long-term trajectory of a society. In this position paper, we identify the risks of overlooking the impact of AI on the future of work and recommend comprehensive transition support towards the evolution of meaningful labor with human agency. Through the lens of economic theories, we highlight the intertemporal impacts of AI on human livelihood and the structural changes in labor markets that exacerbate income inequality. Additionally, the closed-source approach of major stakeholders in AI development resembles rent-seeking behavior through exploiting resources, breeding mediocrity in creative labor, and monopolizing innovation. To address this, we argue in favor of a robust international copyright anatomy supported by implementing collective licensing that ensures fair compensation mechanisms for using data to train AI models. We strongly recommend a pro-worker framework of global AI governance to enhance shared prosperity and economic justice while reducing technical debt.

President Donald Trump's recent visit to the UAE marked a pivotal moment for UAE-U.S. bilateral relations, shining a spotlight on a shared vision for the future. As the UAE and the "New Gulf" pivot from oil to cutting-edge technologies, our partnership with the U.S., rooted in decades of trust, has become a beacon of what's possible when nations collaborate. This trust has paved the way for a bold new chapter: a strategic economic alliance poised to create tens of thousands of high-tech, energy and manufacturing jobs, driving prosperity in both of our countries. At the heart of this collaboration lies the new U.S.-UAE AI Acceleration Partnership. This initiative will advance cooperation in artificial intelligence and other transformative technologies while spurring investment flows between our nations.

Since his first day in office, President Donald Trump has mismanaged negotiations over an end to the war in Ukraine. More than 100 days later, innocent Ukrainians are still dying while the president gets played by Russian President Vladimir Putin – illustrated starkly by the barrages of drones and missiles continually aimed at Ukrainian cities as Trump posts online. It's good to hear Trump finally express some frustration toward Putin and admit that his negotiating tactics aren't working, that, as he says, Putin is "just tapping me along, and has to be dealt with differently." The reasons for this aren't complicated. Instead of increasing his leverage over Russa, Trump offered concession after concession before talks even began.

Hundreds of experts on international affairs believe World War III is inevitable and will likely start within the next 10 years. A new survey of 357 political strategists and foresight practitioners weighed in on the future of humanity, with four in 10 saying a major war involving powerhouses like the US, China or Russia will explode in 2035. By 2035, four in 10 global strategists (40.5%) predicted that a world war involving major nations like the United States, China, or Russia will break out. The majority of those who believe WWIII is coming said that it would likely involve nuclear weapons and battles in outer space. The most notable example pushing respondents to predict would likely be President Donald Trump establishing the US Space Force in 2019.

Surprisingly a number of Earth's waterways remain unmapped, with a significant number in low and middle income countries. Here we build a computer vision model (WaterNet) to learn the location of waterways in the United States, based on high resolution satellite imagery and digital elevation models, and then deploy this in novel environments in the African continent. Our outputs provide detail of waterways structures hereto unmapped. When assessed against community needs requests for rural bridge building related to access to schools, health care facilities and agricultural markets, we find these newly generated waterways capture on average 93% (country range: 88-96%) of these requests whereas Open Street Map, and the state of the art data from TDX-Hydro, capture only 36% (5-72%) and 62% (37% - 85%), respectively. Because these new machine learning enabled maps are built on public and operational data acquisition this approach offers promise for capturing humanitarian needs and planning for social development in places where cartographic efforts have so far failed to deliver. The improved performance in identifying community needs missed by existing data suggests significant value for rural infrastructure development and better targeting of development interventions.

Why you're about to see a lot more drones in the sky For decades, the Federal Aviation Administration (FAA) has restricted people's ability to fly drones in shared airspaces or dense neighborhoods. That's made it hard to deliver futuristic ideas like drones delivering our packages. The agency recently granted Amazon's Prime Air program approval to fly drones beyond the visual line of sight in parts of Texas, and also granted similar waivers to hundreds of police departments around the country. It promises to be the most significant drone decision in decades, and one that will decide just how many drones we all can expect to see and hear buzzing above the US on a daily basis. This story is from The Algorithm, our weekly AI newsletter.

Any effect on the current statistics, he says, will likely still be quite small and won't be "world-changing," so he's not surprised that signs of AI's impact haven't been detected yet. But he's watching closely, with the hope that over the next few years AI could help reverse a two-decade slump in productivity growth that is undermining much of the economy. If that does happen, Syverson says, "then it is world changing." The newest versions of generative AI are bedazzling, with lifelike videos, seemingly expert-sounding prose, and other all too humanlike behaviors. Business leaders are fretting over how to reinvent their companies as billions flow into startups, and the big AI companies are creating ever more powerful models.

The research explores the steerability of Large Language Models (LLMs), particularly OpenAI's ChatGPT iterations. By employing a behavioral psychology framework called OCEAN (Openness, Conscientiousness, Extroversion, Agreeableness, Neuroticism), we quantitatively gauged the model's responsiveness to tailored prompts. When asked to generate text mimicking an extroverted personality, OCEAN scored the language alignment to that behavioral trait. In our analysis, while "openness" presented linguistic ambiguity, "conscientiousness" and "neuroticism" were distinctly evoked in the OCEAN framework, with "extroversion" and "agreeableness" showcasing a notable overlap yet distinct separation from other traits. Our findings underscore GPT's versatility and ability to discern and adapt to nuanced instructions. Furthermore, historical figure simulations highlighted the LLM's capacity to internalize and project instructible personas, precisely replicating their philosophies and dialogic styles. However, the rapid advancements in LLM capabilities and the opaque nature of some training techniques make metric proposals degrade rapidly. Our research emphasizes a quantitative role to describe steerability in LLMs, presenting both its promise and areas for further refinement in aligning its progress to human intentions.