Machine Learning

Building My Personal AI Assistant: Stories, Part 2

Building My Personal AI Assistant: Stories, Part 2

the first part of my construction journey Fernãomy personal AI agent. Now it's time to continue the story and let's…
memweave: Zero-Infra AI Agent Memory with Markdown and SQLite — No Vector Database Required

memweave: Zero-Infra AI Agent Memory with Markdown and SQLite — No Vector Database Required

Disclosure: memweave is an open-source project I built. This article describes the problem it addresses and the design decisions behind…
Introduction to Deep Evidential Regression for Uncertainty Quantification

Introduction to Deep Evidential Regression for Uncertainty Quantification

to evidential deep learning (EDL), a framework for one-shot quantification of epistemic and aleatoric uncertainty. More specifically, we will focus…
How to Expand Claude Cowork

How to Expand Claude Cowork

Me on Claude Code and how you can use it to automate processes and be efficient as a developer. However,…
Prefill Is Compute-Bound. Decode Is Memory-Bound. Why Your GPU Shouldn’t Do Both.

Prefill Is Compute-Bound. Decode Is Memory-Bound. Why Your GPU Shouldn’t Do Both.

a large enterprise size a Kubernetes cluster for real-time inference on their customer-facing LLM product. We started with 64 H100…
Gemini 3.1 Flash TTS: A new AI model for text-to-speech

Gemini 3.1 Flash TTS: A new AI model for text-to-speech

Today, we're introducing Gemini 3.1 Flash TTS, the latest text-to-speech model that delivers improved control, expressiveness and quality — empowering…
From Pixels to DNA: Why the Future of Compression Is About Every Kind of Data

From Pixels to DNA: Why the Future of Compression Is About Every Kind of Data

It’s not about audio and video anymore about compression as an audio/video problem; today, it’s about all-kind-of-data compression: genomes, point clouds,…
From OpenStreetMap to Power BI: Visualizing Wild Swimming Locations

From OpenStreetMap to Power BI: Visualizing Wild Swimming Locations

sport is orienteering and, when I am planning a vacation, the first item I buy is a map of the…
RAG Isn’t Enough — I Built the Missing Context Layer That Makes LLM Systems Work

RAG Isn’t Enough — I Built the Missing Context Layer That Makes LLM Systems Work

TL;DR a full working implementation in pure Python, with real benchmark numbers. RAG systems break when context grows beyond a…
Turn your best AI information into one-click tools in Chrome

Turn your best AI information into one-click tools in Chrome

People use AI in Chrome to help them do more on the web – whether that's answering questions, comparing information…
Back to top button