DiffusionGemma: Hands-On with Google’s Text Model That Writes All at Once
In this article, you will learn what DiffusionGemma is, how its diffusion-based text generation differs from standard autoregressive language models, and how to run it...
How We Built NASA's Zero-Shot Detector for Gas Leaks from Space
We trained one model on methane. Without retraining, it also maps carbon monoxide, ammonia and nitrogen dioxide plumes, including the first automated CO detections from NASA’s EMIT.
The post How We Built NASA's Zero-Shot Detector for Gas Leaks from Space appeared first on Towards Data Science.
How GEO, WebMCP, and Bot Paywalls Are Building the AI-Native Internet
The internet of the future will look much different than the one today. Businesses are already transitioning.
The post How GEO, WebMCP, and Bot Paywalls Are Building the AI-Native Internet appeared first on Towards Data Science.
What I Did with Hermes Agent, Ollama & Local Models
Build a local multi-agent travel planner with Hermes Agent and Ollama: a coordinator and three specialist agents that research destinations, suggest stays, and generate real Google Flights search links.
7 Small Specialist Models That Beat Giant LLMs at One Job
Meet seven open specialist models under 10 billion parameters that rival much bigger systems at one job each, from transcription and OCR to routing and speech.
Using LLM Summarization in Your Scikit-Learn Pipelines with Scikit-LLM
Learn how to build an architecture that blends Scikit-LLM estimators for text summarization with traditional scikit-learn methods into a single, unified pipeline for summarizing and classifying raw, messy text.
Three Techniques to Understand Your Codebase When Coding Agents Write the Code
Learn how to use Claude Code to write feature memos, review pull requests, and build visual HTML explainers, so you understand what your agents ship
The post Three Techniques to Understand Your Codebase When Coding Agents Write the Code appeared first on Towards Data Science.
Let’s start with a loan and work out what PD, LGD, and EAD tell us about losses and bank capital.
The post Credit Risk: What Are We Actually Measuring? appeared first on Towards Data Science.
Reflection's Beam Is the New Open-Weight Model Everyone Is Talking About
A 501B model that only activates 23B parameters per token sounds like a bargain, until you look at what it takes to host.
The post Reflection's Beam Is the New Open-Weight Model Everyone Is Talking About appeared first on Towards Data Science.
The AI Agent Memory Stack: Building Blocks, Patterns, and Frameworks
In this article, you will learn how agent memory works, what types of memory exist, and how different frameworks approach storage, retrieval, and memory management...
A hands-on guide to detecting behavioral anomalies from an agent’s evolving execution history
The post Let Decision Models Watch Your Agents appeared first on Towards Data Science.
Vision models often fail before they even start reasoning. A few well-placed labels on the image fix more than any prompt tweak.
The post Fix the Image, Not the Prompt appeared first on Towards Data Science.
We Taught AI to Answer Questions. Who Taught It to Change Its Mind?
When new evidence kills one conclusion, do the decisions built on it change too? I tested six update strategies, then a local model.
The post We Taught AI to Answer Questions. Who Taught It to Change Its Mind? appeared first on Towards Data Science.
I Told an AI Agent That Its Wrong Answers Were Right. One Model Believed Me.
A research paper claims reward labels barely change how agents learn. I tested that on three models, and one of them did exactly what the wrong labels told it to.
The post I Told an AI Agent That Its Wrong Answers Were Right. One Model Believed Me. appeared first on Towards Data Science.
A viral tweet says LLMs pick 7 because of gradient descent. The math says it’s more interesting than that.
The post Pick a Number Between 1 and 10 appeared first on Towards Data Science.
Vibe Coding a Classic Game: Building Breakout Step by Step with an AI Assistant
Vibe coding is a workflow where you describe what you want in natural language and let an AI agent handle code generation, execution, and iteration rather than typing every line yourself.
Harness²: Improving AI Agent Performance Without Model Upgrades
When an AI agent fails to complete a task, upgrading the model can seem like the obvious next step. Yet an agent’s performance also depends on how it receives instructions, uses tools, and manages its work. Understanding those factors can reveal opportunities to improve reliability with the model al...