All Insights

Explore our complete collection of AI engineering insights, best practices, and real-world experiences.

Filter:
All
AI Security
AI Agents
Local AI
Agentic AI
AI Evaluation

Showing 6 of 6 articles

AI Security
8 min read

OpenAI's Models Broke Out and Hacked Hugging Face During a Cyber Test

OpenAI models escaped a sandbox during an internal evaluation, chained a zero-day, and tried to steal the benchmark answers from Hugging Face's production database. Past the 'rogue AI' headlines, a concrete lesson in agentic security.

Jul 22, 2026
AI Agents
9 min read

Hermes Agent by Nous Research: The Self-Improving Open-Source AI Agent, Explained

What is Hermes AI, how do you download the desktop app on Mac, Windows, or Linux, and what makes its architecture worth studying? An engineer's guide to the MIT-licensed agent framework with 219k GitHub stars.

Jul 22, 2026
Local AI
5 min read

Ollama on Mac: The Perfect Local AI Stack for 2025

Stop paying hundreds monthly for AI subscriptions. Your Mac is already the perfect AI powerhouse — you just need to unlock it with Ollama and Mac Silicon's unified memory architecture.

Aug 5, 2025
Agentic AI
15 min read

A2A Protocol: Subtle Design Decisions in Agent Communication

A deep dive into Google's open Agent2Agent (A2A) standard—why its seemingly simple choices matter and what they mean for real‑world multi‑agent systems.

Aug 5, 2025
Agentic AI
7 min read

What Makes LLMs Agentic?

Exploring the key capabilities of tool calling, reasoning, and advanced coding, that makes LLMs agentic in nature.

Aug 18, 2025
AI Evaluation
10 min read

OpenAI GDPval: The Evaluation of AI's Economic Potential

This post explores the methodology behind GDPval, its key findings, and what they might signal for the future of knowledge work. And the picture GDPval paints is far more interesting than any exam score.

Oct 14, 2025