People often treat an AI model as if it is the entire product. They compare Claude, Codex, Gemini, and local models, then assume the biggest model produces the best result. That misses a major part of what makes an AI coding agent useful. I can take the exact same model, give it the same task, … Read more

Unsloth has released a new 4-bit version of Qwen3.6 that it describes as up to 2.5 times faster. The release uses NVIDIA’s NVFP4 format, and it can run locally on a single Blackwell GPU. That immediately caught my attention, because the headline number sounds excellent, but data center benchmark figures don’t always map cleanly to … Read more

Loop engineering has become one of those AI terms that can mean almost anything, depending on who is using it. Some people present it as the biggest shift in AI development. Others dismiss it as while loops and cron jobs with a new label. I think both sides have a point. Loops are not new. … Read more

A few weeks ago, Anthropic published a 36 page playbook on securing AI agents like Claude Code. The timing matters. On one side, I can now give agents far more access than even a year ago. They can read files, call tools, connect to APIs, send messages, write code, and make decisions without stopping every … Read more

DeepSeek keep doing something I wish more AI labs would do. They push model performance forward, then they open source the useful part. This time, the release wasn’t a new language model. It was something more practical for anyone running local AI or serving models in production. It was DSpark, and the key thing to … Read more

Google recently shipped a new open spec called the Open Knowledge Format, or OKF. Their core argument is simple and, frankly, hard to disagree with. Large language models are no longer held back mainly by raw intelligence. They’re held back by context. If a model doesn’t understand your app, your business, your systems, or your … Read more

Baidu recently released an open weights vision language model called Unlimited-OCR, and the name tells you the pitch straight away. The idea is simple. Feed it a long document and let it transcribe the whole thing in one pass, page after page, without the usual slowdown that hits most models as output grows. That grabbed … Read more

Sakana AI and OpenRouter both made a big claim recently. Their message was simple: a single giant model may not be the best way to get frontier level results anymore. That’s a bold claim on its own. The twist is what sits underneath it. Sakana’s Fugu is presented like a model, but the interesting part … Read more

When an AI agent goes looking for information and comes back empty-handed, the usual assumption is that the answer was missing. A lot of the time, that is not the real problem. The answer may have been sitting right there in the source material. It just didn’t survive the trip into a machine-readable format. That … Read more

Every new model release brings the same promise. Better reasoning. Better synthesis. Better scores on the benchmarks. And yet, if you build knowledge agents for real work, the failures that matter most still keep showing up. I see this especially in retrieval-based systems. The model pulls in source material, then produces something that looks polished … Read more