LLMs

Get the most out of each coding model to have a very powerful coding setup

The hidden cost of probabilistic outputs in systems that demand reliability

Building a knowledge base for AI models isn’t a one-time task but an iterative process of refinement.

Prompt Kit from Use AI To Organize Your Project Files Before You Ask It To Write

Build-time governance in the era of infinite syntax

Guidelines for programming when code is cheap.

The architecture behind a portable knowledge layer and the automation that keeps it alive.

A 12-question reality check on how GenAI is actually failing in software teams right now. Real studies, real citations, three minutes.

Tooling doesn’t break at a small scale—it breaks when teams move to production. AI adoption accelerates, so does the number of tools available to them.

A context layer puts your warehouse schema, joins, metric definitions, and business knowledge in one reviewable place so data agents query governed context instead of guessing field names. A look at how it works, and at ktx, the open-source context layer.

Where is your intelligence located? In your brain? It is a simplistic answer. A better model is that your intelligence is embodied. Consider a cook working at an expensive restaurant. He has all his favorite knives and cooking instructions, placed exactly where he wants them. His kitchen is part of his intelligence, of his skills. … Continue reading Embodied cognition and agentic AI

In my predictions for 2030 I wrote that tech writers would be using specialized LLMs, running locally on powerful hardware. I see hints of this move to “local first” among engineering pundits, but we’re not there yet, in part because of how much more powerful connected frontier models are. That doesn’t mean we can’t experiment, though. That’s precisely what I did last week, trying to fine tune an instruct model to write like a software technical writer from the 80s and 90s.

Keep an overview of all your coding agents that run in parallel

A breakdown of AI agent security approaches -- identity, governance, gateway, and EDR -- and where Runtime Assurance fills the gap.

LibreChat brings together all your AI conversations in one unified, customizable interface.

Caching, lazy-loading, routing, compaction, and more

Watch now | The first useful agent workflow is not generation. It is getting the work surface into shape.

Watch now | Microsoft plans to spend roughly $190 billion this year and still expects to run short on capacity.

Move LLM safeguards out of AGENTS.md: how agent hooks plus nano-staged run linters on changed files only, cut tokens, and tighten the agent's feedback loop

Fabricated case citations generated by AI are appearing in court filings at an accelerating rate. Combined with other tracking efforts, we have identified over 1,000 filings containing hallucinated citations from self-represented (pro se) litigants and lawyers alike.

Watch now | The AI work your company cannot see is the AI work your company cannot learn from.

The production trade-offs that only appear once your model is live.

These MCP servers make my local LLM even better.

For AI engineers who want to understand every step, not just call the library

Zaya1-8B is a huge shift in LLMs, and the results are impressive.

Most LLM failures in production aren’t random — they’re predictable. I kept hitting broken JSON, silent failures, and outages that froze my entire app. Prompt engineering didn’t fix it. So I built a control layer above the model — and took structured output reliability from 0% to 100% without changing a single prompt.

Think of it as the Linux desktop problem, all over again

A 1,000 libraries, 90% coverage, 1,700 in API tokens. Nobody typed a single test by hand.

Everybody is building agent skills, but not all skills are created equal. Here are some recent research papers that empirically show best practices to build them.