GoKawiil
Tech News
A technical blog post examines the common practice of AI agent designers asking large language models to output a numeric confidence or probability score alongside their answers. The author argues there is no sound basis for trusting these numbers, contrasting them with how a human forecaster's confidence is grounded in historical data and a consistent updating process.
Swiss weather tech company Meteomatics says its drones can gather atmospheric data more quickly and accurately than traditional weather balloons. Unlike balloons, which launch at fixed times and are discarded after a single use, the company's drones can be deployed on demand to track developing weather conditions like storms.
Microsoft researchers published a study in Nature describing a machine learning system that corrects bias in existing physics-based and AI weather models, improving forecast accuracy two to six weeks ahead. The tool, now available as open-source software, can run on standard CPUs rather than requiring supercomputers or powerful GPUs.
Researchers describe a probabilistic forecasting method for predicting weather two to six weeks ahead, built on ERA5 reanalysis data from 1979-2026 and evaluated using ECMWF's AI Weather Quest competition framework. The approach forecasts temperature, precipitation and sea-level pressure as probability distributions across climatological quantile bins, scored using the Ranked Probability Skill Score.
The U.S. Air Force has awarded WindBorne Systems a contract worth up to $49 million for atmospheric data collected by its fleet of roughly 700 autonomous weather balloons. The deal, awarded without competitive bidding, lets the Air Force order data by region and time as needed, with $1.7 million in orders placed so far.
A CNET reviewer spent several months testing Amazon's Alexa Plus, Google's Gemini for Home and Apple's Siri AI for weather forecasting accuracy in a high-desert city with microclimates. The test found Alexa Plus gives the longest, most detailed responses—including wind, air quality and 'feels like' temperatures—but occasionally mispredicted rain and tended to overestimate high temperatures.
Google has introduced WeatherNext 3, a new AI-driven forecasting system meant to replace or augment traditional numerical weather prediction methods. The system aims to deliver faster, less computationally expensive forecasts while maintaining or improving accuracy compared to physics-based models.