RAG: Giving AI Agents Access to the Knowledge They Need
How retrieval-augmented generation helps AI agents find and use the knowledge they need.
Magnitude 2.5+ over the past 24 hours.
Loading recent earthquakes…
How retrieval-augmented generation helps AI agents find and use the knowledge they need.
Follow a CSV export task to see how an agent harness connects model decisions to tools, permissions and checks.
Recent technical articles on seismic analytics, scientific computing, numerical modeling, and production data workflows.
A simple earthquake-catalog example explains what the Model Context Protocol does, who introduced it, and how it connects AI applications to outside tools.
A simple shop-and-courier analogy explains how TCP delivers data, TLS protects it, and HTTP gives a website request its meaning.
A three-station seismic matched-filter experiment shows how repeating waveform shapes reveal small earthquake candidates, and why strong matches still need v...
How human comparisons become a training signal, where DPO fits, and why useful AI agents still need independent checks.
How neuroscience, autonomous laboratories, and language-model research can inform agents that preserve evidence and revise their beliefs.
Turn a GitHub release into a citable research archive, share supporting data, and choose the right DOI for your paper.
How expected information gain helps AI agents choose the next observation, with Shannon entropy, a worked building-monitoring example, and practical limits.
An agentic harness gives an AI model tools, context, memory, permissions, and feedback. See how the pieces work together in a scientific Python workflow.
Autoencoders learn compact representations by reconstructing seismic data. This tutorial explains their use in compression, denoising, representation learnin...
An unexpected drop in a building’s natural frequency is the structure reporting that it has lost stiffness — usually the first sign of damage. Here is why to...
Foundation models ask whether one pretrained representation of seismic waveforms can support picking, detection, classification, and other downstream tasks—w...
A compact macOS setup with two Alfred workflows for turning caffeinate on and off, plus SwiftBar for keeping the current status visible in the menu bar.
A simple earthquake-catalog example explains what the Model Context Protocol does, who introduced it, and how it connects AI applications to outside tools.
A simple shop-and-courier analogy explains how TCP delivers data, TLS protects it, and HTTP gives a website request its meaning.
A three-station seismic matched-filter experiment shows how repeating waveform shapes reveal small earthquake candidates, and why strong matches still need v...
How human comparisons become a training signal, where DPO fits, and why useful AI agents still need independent checks.
How neuroscience, autonomous laboratories, and language-model research can inform agents that preserve evidence and revise their beliefs.
Turn a GitHub release into a citable research archive, share supporting data, and choose the right DOI for your paper.
How expected information gain helps AI agents choose the next observation, with Shannon entropy, a worked building-monitoring example, and practical limits.
An agentic harness gives an AI model tools, context, memory, permissions, and feedback. See how the pieces work together in a scientific Python workflow.
Autoencoders learn compact representations by reconstructing seismic data. This tutorial explains their use in compression, denoising, representation learnin...
An unexpected drop in a building’s natural frequency is the structure reporting that it has lost stiffness — usually the first sign of damage. Here is why to...
Foundation models ask whether one pretrained representation of seismic waveforms can support picking, detection, classification, and other downstream tasks—w...
A compact macOS setup with two Alfred workflows for turning caffeinate on and off, plus SwiftBar for keeping the current status visible in the menu bar.