Meteosource – Hyper-local weather API based on improved ML models
Hi HN, I am excited to share the new version of my weather API with you. It offers even more accurate forecasts than before, thanks to updates to our proprietary ML model. My weather forecast website initially started as a personal project. Later, it became more professional, and recently, we have evolved into an advanced weather API. Our goal from the beginning has been to offer affordable yet superior services. To achieve high accuracy, we incorporated machine learning into our calculations. Our forecasts pull data from multiple sources and use proprietary numerical weather models. These…
In plain words
Meteosource is a weather API that provides hyper-local forecasts using machine learning models trained on multiple data sources. It offers minute-by-minute predictions for the next hour and refines forecasts for specific locations using surrounding environmental data. The service is designed for developers and applications requiring accurate weather information at affordable rates, with improved accuracy compared to previous versions through updates to its proprietary ML models.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, I am excited to share the new version of my weather API with you. It offers even more accurate forecasts than before, thanks to updates to our proprietary ML model. My weather forecast website initially started as a personal project. Later, it became more professional, and recently, we have evolved into an advanced weather API. Our goal from the beginning has been to offer affordable yet superior services. To achieve high accuracy, we incorporated machine learning into our calculations. Our forecasts pull data from multiple sources and use proprietary numerical weather models. These models also learn from historical data to reduce bias. This applies to hyper-local forecasts as well, where each point is further refined based on surrounding data. In addition, you will find advanced features like a minute-by-minute forecast for the next hour, updated every ten minutes. I would be grateful for all your thoughts and any ideas!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
