We present Ask WhAI, a systems-level framework for inspecting and perturbing belief states in multi-agent interactions. The framework records and replays agent interactions, supports out-of-band queries into each agent's beliefs and rationale, and enables counterfactual evidence injection to test how belief structures respond to new information. We apply the framework to a medical case simulator notable for its multi-agent shared memory (a time-stamped electronic medical record, or EMR) and an oracle agent (the LabAgent) that holds ground truth lab results revealed only when explicitly queried. We stress-test the system on a multi-specialty diagnostic journey for a child with an abrupt-onset neuropsychiatric presentation. Large language model agents, each primed with strong role-specific priors ("act like a neurologist", "act like an infectious disease specialist"), write to a shared medical record and interact with a moderator across sequential or parallel encounters. Breakpoints at key diagnostic moments enable pre- and post-event belief queries, allowing us to distinguish entrenched priors from reasoning or evidence-integration effects. The simulation reveals that agent beliefs often mirror real-world disciplinary stances, including overreliance on canonical studies and resistance to counterevidence, and that these beliefs can be traced and interrogated in ways not possible with human experts. By making such dynamics visible and testable, Ask WhAI offers a reproducible way to study belief formation and epistemic silos in multi-agent scientific reasoning.

With the rapid rise of large language models (LLMs) in medicine, a key question is whether they can function as competent pediatricians in real-world clinical settings. We developed PEDIASBench, a systematic evaluation framework centered on a knowledge-system framework and tailored to realistic clinical environments. PEDIASBench assesses LLMs across three dimensions: application of basic knowledge, dynamic diagnosis and treatment capability, and pediatric medical safety and medical ethics. We evaluated 12 representative models released over the past two years, including GPT-4o, Qwen3-235B-A22B, and DeepSeek-V3, covering 19 pediatric subspecialties and 211 prototypical diseases. State-of-the-art models performed well on foundational knowledge, with Qwen3-235B-A22B achieving over 90% accuracy on licensing-level questions, but performance declined ~15% as task complexity increased, revealing limitations in complex reasoning. Multiple-choice assessments highlighted weaknesses in integrative reasoning and knowledge recall. In dynamic diagnosis and treatment scenarios, DeepSeek-R1 scored highest in case reasoning (mean 0.58), yet most models struggled to adapt to real-time patient changes. On pediatric medical ethics and safety tasks, Qwen2.5-72B performed best (accuracy 92.05%), though humanistic sensitivity remained limited. These findings indicate that pediatric LLMs are constrained by limited dynamic decision-making and underdeveloped humanistic care. Future development should focus on multimodal integration and a clinical feedback-model iteration loop to enhance safety, interpretability, and human-AI collaboration. While current LLMs cannot independently perform pediatric care, they hold promise for decision support, medical education, and patient communication, laying the groundwork for a safe, trustworthy, and collaborative intelligent pediatric healthcare system.

How conspiracy theories infiltrated the doctor's office Every day, physicians and therapists work to keep their patients safe. As anyone who has googled their symptoms and convinced themselves that they've got a brain tumor will attest, the internet makes it very easy to self-(mis)diagnose your health problems. And although social media and other digital forums can be a lifeline for some people looking for a diagnosis or community, when that information is wrong, it can put their well-being and even lives in danger. Unfortunately, this modern impulse to "do your own research" became even more pronounced during the coronavirus pandemic. We asked a number of health-care professionals about how this shifting landscape is changing their profession. They told us that they are being forced to adapt how they treat patients.

Things to Do in L.A. Tap to enable a layout that focuses on the article. California has a strict vaccine mandate. Will it survive the Trump administration? Dr. Neville Anderson, right, tries to distract Perry Roj, 4, while nurse Breanna Kirby gives her a DTaP polio vaccination. Her mom, Devin Homsey, holds her tight at Larchmont Pediatrics.

The first fully human-capable AI agents for healthcare are now being used across the country. Artificial intelligence is gaining more of parents' trust than actual doctors. That's according to a new study from the University of Kansas Life Span Institute, which found that parents seeking information on their children's health are turning to AI more than human health care professionals. The research, published in the Journal of Pediatric Psychology, also revealed that parents rate AI-generated text as "credible, moral and trustworthy." More than 100 parents ranging from 18 to 65 years old were asked to rate text generated by either a human doctor or ChatGPT (the AI chatbot made by OpenAI) under the supervision of an expert.

You have likely heard of ChatGPT, the artificial intelligence chatbot that can create original college essays that don't get flagged by plagiarism-detection software. Of course, it can do many things beyond confounding educators and delighting students. It can, for instance, write computer code. And, I discovered, give travel planning advice. To see how useful its travel suggestions might be, I began by asking what there is to see in Uturoa, the main town on the French Polynesian island of Raiatea.

Artificial intelligence (AI) is responsible for driving autonomous vehicles, powering intelligent assistants such as Alexa and Siri, and placing annoying advertisements on web pages. AI has also improved many aspects of pediatric medicine, and played an important role in the COVID-19 pandemic. Voice recognition/dictation software is an example of AI that is currently used in pediatric practice. Today, Dragon Medical One from Nuance Communications, the most widely used voice recognition medical software, boasts a vocabulary of 300,000 words and integrates vocabularies for 90 medical specialties. By integrating deep learning (DL), the software covers the nuances of the user's speech patterns and improves over time, achieving 99% accuracy.1

Care and Feeding is Slate's parenting advice column. Have a question for Care and Feeding? Submit it here or post it in the Slate Parenting Facebook group. My husband and I both have full-time jobs and an 18-month-old son. I am pregnant with our second child, due in February. Since our son was born, my husband seems to have regressed.

Training a doctor takes years of grueling work in universities and hospitals. Building a doctor may be as easy as teaching an AI how to read. Artificial intelligence has taken another step towards becoming an integral part of 21st-century medicine. New research out of Guangzhou, China, published February 11th in Nature Medicine Letters, has demonstrated a natural-language processing AI that is capable of out-performing rookie pediatricians in diagnosing common childhood ailments. The massive study examined the electronic health records (EHR) from nearly 600,000 patients over an 18-month period at the Guangzhou Women and Children's Medical Center and then compared AI-generated diagnoses against new assessments from physicians with a range of experience.

The study: The system was trained on medical records from 1.4 million visits by 567,498 patients under 18 to a medical center in Guangzhou, China. A team distilled this information into keywords linked to different diagnoses, and then fed these into the system to help it detect one of 55 diseases. The system managed to diagnose conditions ranging from common ailments like influenza and hand-foot-mouth disease to life-threatening conditions like meningitis with 90% to 97% accuracy. Its accuracy was compared with that of 20 pediatricians. It managed to outperform the junior ones, but more senior doctors had a higher success rate.