If your access control lives in a prompt, it isn’t access control. Authorization decisions must be deterministic and enforced before an LLM ever sees data. Treating AI as a policy engine is a category error with real consequences.

Anthropic installed an AI-powered vending machine in the WSJ office. The LLM, named Claudius, was responsible for autonomously purchasing inventory from wholesalers, setting prices, tracking inventory, and generating a profit. The newsroom’s journ

GitHub release .NET Native AOT A local-first document summarization tool that uses LLMs (via Ollama), vector search (Qdrant), and document conversion...

The basic concept of human intelligence entails self-awareness alongside the ability to reason and apply logic to one’s actions and daily life. Despite the very fuzzy definition of ‘hum…

LLMs Generate Incorrect Results. But Results Can Be Verified.

thoughts on programming. Contribute to Dobiasd/articles development by creating an account on GitHub.

Three AI anti-patterns that consistently frustrate development teams, and how to avoid them.

Disambiguating LLMs from other machine learning tech is the first step to making sense of the current AI boom.

How to manage a team of AI assistants in a virtuous cycle of improvement. The LLM flywheel effect is a new workflow for developers to adopt.

Has anyone noticed that news stories have gotten shorter and pithier over the past few decades, sometimes seeming like summaries of what you used to peruse? In spite of that, huge numbers of people…

The extreme hype surrounding generative AI and technologies like LLMs has been exhausting over the last few years. Coupled with fear-based marketing...

Go beyond storing `role:content` pairs and model your whole set of interactions when building LLM powered applications

LLMs can lower the burden of writing useful alt text for images, with the right prompting.

If you’ve been following the AI space for a while, the MCP acronym might be a familiar sight: it’s an open standard for connecting large language models (LLMs) to tools and data. Without the ability to use tools and get data, AI agents are powerless, their knowledge limited to their training set and the context at hand. Giving in to my curiosity, I created an MCP server to demystify this piece of tech and gain a better understanding of its potential. Not all is rosy, but if there’s a place where doc tools need to grow, it’s this.

Instead of writing crap tons of parsing code for LLMs you can just use functions. It's easy.

Weave combines LLMs and domain-specific machine learning to understand engineering work.

Collect some data, feed it to various language models and see what comes out.

This new guide documents experiments with using LLMs to summarize and provide interesting insights into data collected from an environmental sensor. It is not a fully fleshed out project that is re…

Note: This post is complemented by a presentation I gave at KazHackStan 2025. The slides for that talk can be found here, or in pptx format here..

AI and LLMs pose a particularly visceral threat to the typing class. Writers, editors, poets, freelancers, marketing copywriters and others are voicing reasonable (and unreasonable) objections to t…

No one likes to be wrong. But perhaps what bothers people even more than making a mistake is being made a fool, being tricked or duped. It's no surprise then that many folks bristle at the assertion that "AI" is a con. They stamp their feet and insist that no,

Automatically filter sensitive information before sending it to external services or APIs, such as chatbots and LLMs.

More than two years into the AI hype, here’s a grounded overview of this period from the perspective of a regular software developer.

Learn how to make unreliable AI APIs reliable using proven distributed systems patterns. Real example: reduced LLM costs from $20 to $0 with transactional outbox.

Random thoughts, articles and projects by a chronic overengineer.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.