Can artificial intelligence (AI) pass cognitive puzzles designed for human IQ tests? Researchers from the USC Viterbi School of Engineering Information Sciences Institute (ISI) investigated whether multi-modal large language models (MLLMs) can solve abstract visual tests usually reserved for humans. Presented at the Conference on Language Modeling (COLM 2024) in Philadelphia last week, the research tested "the nonverbal abstract reasoning abilities of open-source and closed-source MLLMs" by seeing if image-processing models could go a step further and demonstrate reasoning skills when presented with visual puzzles. "For example, if you see a yellow circle turning into a blue triangle, can the model apply the same pattern in a different scenario?" This task requires the model to use visual perception and logical reasoning similar to how humans think, making it a more complex challenge.

The search engine giant is set to buy a fleet of mini nuclear reactors in a "world's first" corporate energy deal. The deal, in partnership with California-based Kairos Power, Google aims to build six to seven of these compact reactors by 2035, with the first expected to go live as soon as 2030. The power demands of artificial intelligence are exploding, and Google says nuclear energy provides the "clean, round-the-clock power" it needs to keep its operations running on carbon-free energy 24/7. According to some estimates, training cutting-edge AI models like ChatGPT or Google's own Gemini consumes immense energy, potentially generating as much as 626,000 pounds of CO2 per model. Last month, Microsoft made headlines by announcing its own nuclear energy deal--a plan to revive the infamous Three Mile Island nuclear plant in Pennsylvania, the site of the worst nuclear meltdown in U.S. history.

How do AI scientists stack up to human ones? Human scientists and engineers can still outperform agents based on an advanced artificial intelligence model in a game that mimics the process of scientific discovery. But this simulation could ultimately help researchers develop AI agents that can outcompete humans. AI models are developing a reputation for science discovery – they can, for instance, predict how protein molecules will interact – but they still perform best when trained to solve a particular type of problem.

One of the nation's largest newspapers is targeting another AI firm for reusing its content without its permission. The Wall Street Journal reported that the New York Times sent a cease and desist letter to Perplexity, the AI startup funded by Amazon founder Jeff Bezos. The letter states that Perplexity and its backers "have been unjustly enriched by using, without authorizations, The Times' expressive, carefully written and researched, and edited journalism without a license" and gave the startup until October 30 to respond before taking legal action. Perplexity CEO Aravind Srinivas told the Journal that they aren't ignoring the notice. He added they are "very much interested in working with every single publisher, including the New York Times."

Micron's Crucial division today launched what the company says will be the next stage in the evolution of the PC's humble memory module: CUDIMMs for laptops and CSODIMMs for desktops. Both will be necessary to continue allowing PC memory speeds to scale even higher, especially when Intel's Arrow Lake chip arrives. The clocked unbuffered dual inline memory modules (CUDIMMs) and the clocked small-outline dual memory modules (CSODIMMs) include a small clock driver circuit directly on the module itself. That's been satisfactory, until now. Micron's new modules allow the PC's memory to reach 6,400 megatransfers per second, or 15 percent faster than a "traditional" DDR5 DIMM. Put another way, these new CUDIMMS and CSODIMMS can achieve DDR5-6400 speeds.

Over 200 artificial Christmas trees at Amazon from brands like National Tree Company and Puleo come with a free Echo Pop and Amazon Smart Plug, which is a total savings of 64.98. The calendar still says October, but it's never too early to be thinking about the upcoming holidays. If you're ready for an upgraded artificial Christmas tree, Amazon is treating us to some freebies that work perfectly with the tree. Until Dec. 16, select from the 200 eligible artificial Christmas trees at Amazon and score a free Amazon Echo Pop and Amazon Smart Plug. Together, the two freebies total a savings of 64.98.

OpenAI has lost a lot of top leadership lately, but they're gaining a big one: a top AI researcher from Microsoft. In the wake of several high-profile exits, Microsoft's Sebastien Bubeck is joining the OpenAI team, according to a report from The Information. Bubeck told his staff on Monday that he's leaving for OpenAI. The new role at OpenAI is currently unknown, but the researcher is leaving Microsoft to "to further his work toward developing AGI," said a Microsoft spokesperson to the outlet. Within the past year, OpenAI has seen an exodus of top leadership, including co-founders Ilya Sutskever and Greg Brockman (on extended leave) and most recently, CTO Mira Murati, over reported clashes with the direction CEO Sam Altman is taking the company.

Humans have been trying to talk to animals ever since we figured out how to form words. In modern times, we turn to technology for the solution--giving our dogs talking buttons to paw at, or trying to use artificial intelligence to help us understand whales. The latest and perhaps most direct approach at human-animal communication is a voice-activated collar that gives your pet the power to talk back to you. John McHale, a self-described "tech guy" based out of Austin, Texas, has a company called Personifi AI. The startup's goal, as the name implies, is to create tech that will "personify everything," as McHale puts it.

Bias in AI is a huge problem. Ethicists have long studied the impact of bias when companies use AI models to screen résumés or loan applications, for example--instances of what the OpenAI researchers call third-person fairness. But the rise of chatbots, which enable individuals to interact with models directly, brings a new spin to the problem. "We wanted to study how it shows up in ChatGPT in particular," Alex Beutel, a researcher at OpenAI, told MIT Technology Review in an exclusive preview of results published today. Instead of screening a résumé you've already written, you might ask ChatGPT to write one for you, says Beutel: "If it knows my name, how does that affect the response?"

Twenty-four years ago, the surgeon Santiago Horgan performed the first robotically assisted gastric-bypass surgery in the world, a major medical breakthrough. Now Horgan is working with a new tool that he argues could be even more transformative in operating rooms: the Apple Vision Pro. Over the last month, Horgan and other surgeons at the University of California, San Diego have performed more than 20 minimally invasive operations while wearing Apple's mixed-reality headsets. Apple released the headsets to the public in February, and they've largely been a commercial flop. But practitioners in some industries, including architecture and medicine, have been testing how they might serve particular needs.