Many teams find governance gaps only after a retrieval system surfaces stale or unauthorized content in production. Models, agents, and retrieval workflows all depend on enterprise data. Before any of that data reaches an AI system, teams need to know where it originates, how it’s integrated, whether it meets quality expectations, what context enriches it, who can access it, and how it changes over time.
This checklist gives engineering, data, platform, architecture, and governance teams a structured way to check whether enterprise data is ready for AI use. — Read More
Daily Archives: June 24, 2026
What Is Software, and Will LLMs Replace It?
We’ve all been using LLMs for a while now, and we’ve all been impressed by them. At some point it is natural to ask the question: is this it? Is this what is going to replace software? …I don’t think so, but it’s tempting to believe it.
… LLMs are showing us something genuinely useful: that interfaces can be far more flexible than we assumed. But I don’t think that’s the same as software disappearing into conversation. Let’s look at why. — Read More
Open-Source AI Is Becoming Unstoppable
In February 2026, a Chinese lab released a 745 billion parameter model competitive with the best in the world, GPT and Claude included, and not one piece of it touched an Nvidia chip. Zhipu AI trained GLM-5 start to finish on Huawei’s Ascend hardware, using a software stack Huawei had only just decided to give away for free, specifically so outside developers would stop needing Nvidia’s blessing to compete.
Mark Zuckerberg has compared this moment to an older one. Unix used to mean a handful of companies each building their own closed, incompatible version, until Linux showed up, free and unglamorous, and slowly became the thing the internet now quietly runs on. The comparison is useful, but not exact. Linux gave away its source code and its entire history. Most open AI models still keep their training data to themselves, so outsiders can inspect the result without ever fully knowing how it was made. Open-source AI may well become the Linux of intelligence. It just hasn’t earned the full analogy yet.
That’s the real story here. Not one battle between open and closed, but a dozen separate layers of how AI gets built, run, and paid for, all becoming contestable at the same time: the training process, the hardware underneath it, the architecture inside the model, the data it learns from, what even counts as a model anymore, where it physically runs, and what the internet itself is increasingly made of. — Read More
I Wish I Knew This Before Building an AI Second Brain
My Second Brain is filled with everything I write, webpages I clip, notes I take, my daily logs, my projects, and any conversations with AI that I decide are worth saving. Claude has access to all of it. I don’t even need to tell it to look. Claude knows what’s in my Second Brain; it knows to search for whatever it needs; and knows how to access things when it finds what it’s looking for.
… I only started to see success with this system when I set out a well-defined set of rules for my vault and explicit protocols to manage it. Only then, once I’ve mastered it myself, will I teach an AI agent how to automate it. — Read More
30 Core Agentic Engineering Concepts Every Developer Should Know
A simple guide to AI agents, tools, memory, multi-agent systems, and how to build them safely
… [T]he same few ideas keep coming back again and again. Once you understand the idea, it stops mattering which tool is trending this week. You can look at any new agent tool and quickly understand what it is really doing.
That is the goal of this story. By the end, you will understand 30 core agentic engineering concepts in simple language. So the next time you read an agent post, watch a demo, or see another AI news drop, you will be able to recognize the real idea behind it instead of feeling behind again. — Read More
The Coming Loop
Over the last months I have watched more and more people build something on top of coding agents that feels meaningfully different from just using a coding agent. Some of this happens on top of Pi which is cool to see for sure! The pattern is the same everywhere though: work is put into a queue of sorts, a machine picks it up, attempts it, stops, and then some harness decides whether that was actually the end.
If not, the harness continues the same session, injects another message, starts a fresh session with modified context, or sends the task to another machine. The task stays alive beyond the point where the model by itself would normally have said: “I am done.”
… There is already an agent loop inside every coding agent. The model calls a tool, incorporates the result, calls another tool, reads a file, edits a file, runs tests, and eventually produces some answer. That loop is one we have been quite familiar with for a long time. The other loop is the harness level loop: the loop outside the agent loop. That loop is also not new. We have been doing versions of this since early Claude Code days, but that loop is becoming ever more present in agentic engineering and in recent weeks it has started to dominate the Twitter discourse. — Read More
War by Other Means
Robotic warfare is shifting the source of state power away from citizens to firms. The transition will produce a new social contract.
XIn December 2024, the Ukrainian National Guard’s 13th Khartiia Brigade carried out a combined ground and air assault near the town of Lyptsi. Air assets coordinated with dispersed ground forces bounding from cover to cover. Dozens of attackers overran Russian positions, cleared mines in the vicinity, and laid down a defensive perimeter around the captured territory. But not a single Ukrainian was present on the battlefield.
To achieve this, soldiers piloted a mix of unmanned ground vehicles mounted with machine-gun turrets, aerial drones bristling with grenades and assault rifles, and more conventional kamikaze drones. This experiment allowed the Ukrainians to trade valuable human advantages like spatial awareness and tactical flexibility for the assurance that their only casualties would be robotic. For a country suffering severe manpower shortages, such a tradeoff was welcome amid a gruesome war of attrition fought against an adversary with more than three times its population. — Read More
Making a vintage LLM from scratch
In this blog post, I will share the adventures I had creating my own LLM, from (almost) scratch, trained only on old texts.
I made my own base-training and fine-tuning scripts, data processing pipelines and custom datasets.
(“almost from scratch” means I did use existing programming languages and libraries, I didn’t write in Assembly, just like anyone else who builds an AI “from scratch”…)
The model can be found on HuggingFace: https://huggingface.co/croqaz/vintage-LLM-340m-v1-base ; All the code is open source at: https://github.com/croqaz/vintage-LLM ;
If you want to check bigger Vintage models, see my previous post: Vintage LLM models. — Read More
Rick's Cafe AI 