tutorial
The power of LLama
Running local LLMs isn't just about privacy—it's about cost, control, and understanding how AI really works. Here's where to learn, what to ignore, and how to get started.
Bruno Sofiato
A computer enthusiast since tender age. Passionate to both theory and praxis. Work on both the industry and academy. A Gamer and a metal head.
qwen, mixture-of-experts, ai-agents, tool-calling, self-hosted-llm, agent-world
Qwen-AgentWorld: An Agent Focused Model That Punches Above Its Compute Bill
Qwen's new AgentWorld-35B-A3B highlights a growing trend in local AI: specialized, self-hostable models competing with frontier systems on targeted workloads. The question is increasingly not "Which model is smartest?" but "Which model is best for the job?"
local-ai-inference, small-language-models, llm-cost-optimization, diffusion-language-models, ai-infrastructure
The AI Golden Age Has Passed, Welcome to the AI Golden Age
The first AI golden age was built on renting frontier model compute by the token. The second is built on local inference, small specialized models, and routing architecture that puts the right task on the cheapest capable model.
open-weight-llm, glm-5-2, llm-benchmarks, hugging-face, ai-model-release, vendor-lock-in
GLM 5.2 Goes Open Weight: A Top-Four Model You Can Now Download
GLM 5.2 is now available as an open weight model on Hugging Face, ranking fourth overall and competing directly with closed frontier leaders Mythos, Fable, and Opus 4.8. It is the strongest open weight model tested to date, with no vendor agreement or API required.
abliteration, llm-security, open-weights-models, red-teaming, ai-censorship, cybersecurity, fable, antrophic, mythos
When Availability has become a first-class AI capability metric
The Mythos/Fable blockade revealed a new reality: a model's benchmark score is zero when it's unavailable by decree. In the age of strategic AI, availability has become a capability of its own—and open-weight models are how organizations reclaim it.
agentic-ai, ai-system-design, llm-safety, prompt-injection, ai-architecture, model-routing
Six Fallacies That Break Agentic AI Systems (And How to Design Around Them)
Six false assumptions break most agentic AI systems before they scale. This post names each fallacy, documents the real-world damage it causes, and outlines the design patterns that prevent it.
about-aipster, community
From a WhatsApp Group to an AI Think Tank
How six computer science friends from the late '90s turned a happy hour chat into a collective exploration of artificial intelligence — and why we decided to share what we learn along the way. It started, as many good things do, with a simple question: "Can everyone make it