The evergreen trees give kangaroos, bison, lions, and more extra shelter and fun. Capybaras use donated Christmas trees as wind breaks to protect their habitats. Breakthroughs, discoveries, and DIY tips sent every weekday. The presents are unwrapped, the cookies are crumbs, and that real Christmas tree will become a fire hazard soon enough. Most of us haul it out to the curb for our local sanitation departments to take care of, but some lucky trees make it into the paws of animals living in zoos.

Chain-of-Thought (CoT) reasoning has significantly advanced state-of-the-art AI capabilities. However, recent studies have shown that CoT reasoning is not always faithful, i.e. CoT reasoning does not always reflect how models arrive at conclusions. So far, most of these studies have focused on unfaithfulness in unnatural contexts where an explicit bias has been introduced. In contrast, we show that unfaithful CoT can occur on realistic prompts with no artificial bias. Our results reveal non-negligible rates of several forms of unfaithful reasoning in frontier models: Sonnet 3.7 (16.3%), DeepSeek R1 (5.3%) and ChatGPT-4o (7.0%) all answer a notable proportion of question pairs unfaithfully. Specifically, we find that models rationalize their implicit biases in answers to binary questions ("implicit post-hoc rationalization"). For example, when separately presented with the questions "Is X bigger than Y?" and "Is Y bigger than X?", models sometimes produce superficially coherent arguments to justify answering Yes to both questions or No to both questions, despite such responses being logically contradictory. We also investigate restoration errors (Dziri et al., 2023), where models make and then silently correct errors in their reasoning, and unfaithful shortcuts, where models use clearly illogical reasoning to simplify solving problems in Putnam questions (a hard benchmark). Our findings raise challenges for AI safety work that relies on monitoring CoT to detect undesired behavior.

Harvey Castro talks about how AI could be used in cold cases and the symbiotic relationship between AI and a detective. New Jersey police are deploying new technology to try to break an unsolved case in what some experts believe could be the greatest advancement in cold-case investigations since forensic genetic genealogy caught the infamous Golden State Killer in 2018. A police department in the 70-square-mile town of Middle Township, along with the Cape May County Prosecutor's Office, will use artificial intelligence to try to solve the case of Mark Himebaugh, an 11-year-old child who seemingly vanished on Nov. 25, 1991. In the 30-plus years since Himebaugh went missing, law enforcement's strongest leads are a composite sketch of a person of interest and a theory that a convicted child sex predator, who's currently in prison, is involved. But neither are strong enough to bring charges or even advance the case.

The latest appeal of unmanned aircraft is that they can be deployed in a variety of disaster-ravaged locations. An unmanned drone is prepared to take off March 8 at Woodbine Municipal Airport in South Jersey carrying a "femtocell" that Verizon can fly into an area that loses cellular coverage during a natural or other emergency. CAPE MAY COUNTY, N.J.-- Cell service get clobbered by a hurricane? The rash of devastating storms that knocked out power and phone service to millions in the U.S. last year laid bare how vulnerable those technological lifelines are to extreme weather. Some companies are trying to use one of this decade's coolest developments -- remote-controlled drones -- as a temporary fix.