Blog Home

  • Understanding the Fable 5 Situation: AI Jailbreaking
    By Jorge Pereira • 2026-06-29
    The Fable 5 situation represents a significant moment in the ongoing discourse around AI safety and vulnerabilities. Beyond highlighting the challenges of preventing sophisticated jailbreaks, it intensified discussions among AI developers, security researchers, and policymakers about balancing powerful AI capabilities with effective safeguards. I needed to understand this move, so I researched it a bit…
    Read More

  • Disaggregated Inference: Future of LLM Serving
    By Jorge Pereira • 2026-06-28
    If you’ve ever wondered why your AI chatbot suddenly slows down when you feed it a massive 50-page PDF, you’ve encountered a fundamental bottleneck in modern AI infrastructure. For years, we’ve served LLMs like a one-person kitchen: the same chef (GPU) does all the prep work and all the cooking. But as companies start deploying models at…
    Read More

  • The Fable 5 Situation
    By Jorge Pereira • 2026-06-27
    The “Fable 5 Incident” refers to a major, unprecedented national security intervention by the US government that forced AI lab Anthropic to abruptly pull its most advanced artificial intelligence models, Claude Fable 5 and Claude Mythos 5, from public and commercial access. The event marked the first time a Western government directly intervened to shut…
    Read More

  • Why the Best AI Isn’t One Giant Brain—It’s a Team of Specialists
    By Jorge Pereira • 2026-06-26
    When most of us think about Artificial Intelligence, we picture a single, all-knowing brain. We type a question into a chatbot, and a massive, incredibly smart engine spits out an answer. It’s easy to assume that the secret to a great AI application is simply finding the biggest, smartest, most powerful AI model on the…
    Read More

  • The Most Expensive Model: o1-Pro Deep Reasoning
    By Jorge Pereira • 2026-06-24
    The AI landscape has shifted from a race for sheer size to a race for deep reasoning. In this new era, one model stands alone as an absolute financial and computational outlier: OpenAI’s o1-Pro. As of June 2026, priced at a “reasonable” – just kidding – an astronomical $150.00 per million input tokens and $600.00…
    Read More

  • Demystifying AI Loops: How Modern AI Learns to Self-Correct
    By Jorge Pereira • 2026-06-22
    If you have used a standard AI chat interface, you are probably familiar with traditional prompting. You type a question, wait a few seconds, and get an answer. If the answer is wrong, you type another prompt to fix it. This is called “single-shot” prompting, and while it feels magical at first, it has a…
    Read More

  • The Local AI Revolution: How AMD is Challenging Nvidia
    By Jorge Pereira • 2026-06-21
    For the better part of a decade, Nvidia has dominated the artificial intelligence (AI) landscape, not just with high-performance graphics cards but by building an ecosystem that locked in developers and researchers. Anyone looking to engage in serious AI development was expected to pay the hefty “Nvidia tax.” I have written before about the NVIDIA…
    Read More

  • The Quest for Token Efficiency: Why Every Token Matters Now
    By Jorge Pereira • 2026-06-19
    The artificial intelligence industry has experienced exponential growth in model capabilities over the past few years. As we have moved from models with billions of parameters to systems containing hundreds of billions of parameters, while expanding context windows into the millions of tokens, a new challenge has emerged: token efficiency. Every token carries a cost…
    Read More

  • Beyond OpenRouter: What the rest of the market has to offer
    By Jorge Pereira • 2026-06-17
    Time to revisit The Rise of the Enterprise Token Broker blog post The AI Gateway—the centralized “Token Broker”. I’ll be honest: writing this post feels a little like breaking up with someone you genuinely like. OpenRouter has been part of my daily workflow for two and a half years. It solved a real problem, it…
    Read More

  • The Evolution of AI-Native Development
    By Jorge Pereira • 2026-06-13
    The landscape of software development has undergone a radical transformation in the last few years. As AI evolves from simple autocomplete to autonomous agentic workflows, the tools we use to build software have shifted from passive plugins to active collaborators. 1. The Origins: Codeium and the Autocomplete Era The journey began with Codeium (originally developed…
    Read More

  • AI Agents: From Conversation to Action
    By Jorge Pereira • 2026-06-12
    For the past few years, most people have thought of AI as a chatbot. You ask a question, receive an answer, and the interaction ends there. A new category of technology is changing that model entirely. I have been writing about this for a while — I think my frst post was back in December…
    Read More

  • Exploring MiniMax in June 2026
    By Jorge Pereira • 2026-06-09
    The AI landscape is constantly evolving, and at the forefront of this revolution is the MiniMax series, a family of powerful, efficiency-focused large language models developed by MiniMax, a Shanghai-based AI company. MiniMax models are engineered specifically to excel at high-throughput agentic workflows, long-context comprehension, and complex software engineering tasks. I have been testing MiniMax…
    Read More

Welcome!

JPG

This is my personal site and blog. I post bits and pieces about myLife, myWork, myJourney. They are interesting to me but make them available in the hopes someone else will them interesting, useful and enjoyable!

doodlingjorge.com
Subscribe!


Article Series

Check out one of my article series:

Posts Tags & Categories
Categories: