american woman
Unsupervised decoding of encoded reasoning using language model interpretability
As large language models become increasingly capable, there is growing concern that they may develop reasoning processes that are encoded or hidden from human oversight. To investigate whether current interpretability techniques can penetrate such encoded reasoning, we construct a controlled testbed by fine-tuning a reasoning model (DeepSeek-R1-Distill-Llama-70B) to perform chain-of-thought reasoning in ROT-13 encryption while maintaining intelligible English outputs. We evaluate mechanistic interpretability methods--in particular, logit lens analysis--on their ability to decode the model's hidden reasoning process using only internal activations. We show that logit lens can effectively translate encoded reasoning, with accuracy peaking in intermediate-to-late layers. Finally, we develop a fully unsupervised decoding pipeline that combines logit lens with automated paraphrasing, achieving substantial accuracy in reconstructing complete reasoning transcripts from internal model representations. These findings suggest that current mechanistic interpretability techniques may be more robust to simple forms of encoded reasoning than previously understood. Our work provides an initial framework for evaluating interpretability methods against models that reason in non-human-readable formats, contributing to the broader challenge of maintaining oversight over increasingly capable AI systems.
- North America > United States > Illinois > Sangamon County > Springfield (0.14)
- North America > United States > Illinois > Cook County > Chicago (0.07)
- North America > United States > California > Sacramento County > Sacramento (0.05)
- (22 more...)
On this day in history, June 18, 1983, astronaut Sally Ride becomes first American woman in space
Astronaut Sally Ride became the first American woman in space on this day in history, June 18, 1983. Born on May 26, 1951, in Los Angeles, Ride earned bachelor's degrees in English and physics from Stanford University in California before staying at Stanford and earning a PhD in physics in 1978. Shortly before earning her doctorate, Ride saw an ad for a newspaper that piqued her interest. NASA was recruiting for astronauts -- and, for the first time, the agency would include women in its astronaut class. "Over 8,000 men and women applied to the space program that year. Of the 35 individuals accepted, six were women, and I was one of them. This was in January 1978," said Ride in quotes listed on a tribute page on NASA's website.
- North America > United States > California > Los Angeles County > Los Angeles (0.25)
- North America > United States > New York (0.05)
- North America > United States > Florida > Brevard County > Cape Canaveral (0.05)
- North America > United States > California > San Diego County > San Diego (0.05)
- Government > Space Agency (1.00)
- Government > Regional Government > North America Government > United States Government (1.00)
A dead NASA satellite is returning to Earth after 38 years in space
After nearly four decades in space, NASA's retried Earth Radiation Budget Satellite (ERBS) is about to fall from the sky. On Friday, the agency said the likelihood of wreckage from ERBS harming anyone on Earth is "very low." NASA expects most of the 5,400-pound satellite will burn up upon re-entry. Earlier this week, the Defense Department predicted ERBS would re-enter the Earth's atmosphere on Sunday at approximately 6:40PM ET, give or take 17 hours. While it may be a household name, the Earth Radiation Budget Satellite had anything but a dull history.
- Government > Space Agency (1.00)
- Government > Regional Government > North America Government > United States Government (1.00)
New AI Detects Breast Cancer from Ultrasounds
Artificial intelligence (AI) machine learning is rapidly transforming how physicians, clinicians, pathologists, and health care providers diagnose patient conditions. A recent NYU Langone Health study published in Nature Communications shows how AI applied to ultrasound images can identify breast cancer with radiologist-level accuracy, reduce requested biopsies by 27.8 percent, and significantly decrease false positive rates of breast cancer by 37 percent. "In this work, we present an AI system that achieves radiologist-level accuracy in identifying breast cancer in ultrasound images," wrote Krzysztof Geras, PhD., the study senior investigator and assistant professor at NYU Grossman School of Medicine, in collaboration with co-investigator and radiologist Linda Moy, MD. a professor at NYU Grossman School of Medicine, and their research colleagues. Both Geras and Moy are members of the Perlmutter Cancer Center. Breast cancer is a leading cause of death among women worldwide.
Sally Ride's NASA Career Was Even More Interesting Than You Thought
Sally Ride was the first astronaut to operate the robotic Canadarm. We know Sally Ride, born on this day in 1951, as the first American woman in space (and since her death in 2012, we've known her as the only openly LGBT American astronaut so far) but she did much more than just show up for the ride, whether on her first Space Shuttle flight or during her 34-year career as an astronaut and physicist. It's easy for the basic fact of Ride's identity to eclipse her actual work. Her 1983 Challenger flight was groundbreaking, but in many ways the rest of her career is far more interesting; Ride herself certainly thought so, based on her comments in several interviews. From designing Canadarm 1 to investigating the loss of two Space Shuttles, and from X-rays in the interstellar medium to the physics of lasers, here's a look at what the first American woman in space actually did.
- North America > United States (1.00)
- North America > Canada (0.06)
- Asia > Indonesia (0.06)
- Government > Space Agency (1.00)
- Government > Regional Government > North America Government > United States Government (1.00)
Hot holiday toys: Oonies, Fingerlings, Legos and some 'surprises'
The holidays are upon us, which means toys are popping up everywhere. There are Hatchimals and Shopkins, Fingerlings and Oonies, and of course updates on classics like Legos and Nintendo. The most popular of the bunch have already begun selling out online and in stores. Shoppers are projected to spend an average of $967.13 this holiday season, a 3.4 percent increase from last year, with the bulk of that money going toward gifts for family members, according to the National Retail Federation. Spending on toys is also on the rise, with roughly 40 percent of adults saying they plan to buy toys this year, up from 29 percent five years ago, according to data from Deloitte.
- Retail (1.00)
- Media > News (0.66)
- Leisure & Entertainment > Games > Computer Games (0.56)
- Media > Film (0.52)
CovertBand tracking system hijacks smart devices to record
Smart devices such as Google Home and Amazon Echo could be transformed into surveillance tools that track your every move, according to scientists. The CovertBand tracking system uses the built-in microphone as a receiver to pick up reflected sound waves - and is so powerful it can record what you're doing through a wall. The smart device then transmits this information to the attacker, who could be a few feet away or halfway across the globe. The researchers tested CovertBand using a Samsung Galaxy S4 smartphone hooked up to a portable speaker (pictured). Using a software code called CovertBand researchers turned a smart device into a sonar system which can take over built-in microphones and speakers in a smart device - that can be controlled remotely.
Can machine learning tackle the top killer of American women?
According to the Women's Heart Foundation, coronary artery disease is the leading cause of death in women. More than twice as many women die from cardiovascular disease as from all forms of cancer combined. Evaluation for suspected coronary disease differs in women because of frequently misleading results provided by treadmill testing without imaging. Gender differences have been observed in treatment practices, and the optimal approach for women has yet to be established. This week they announced the launch of myWanda, the first and only mobile application specifically aimed at empowering women to improve the health of their hearts.