A from-the-ground-up walkthrough of how modern LLMs work, from tokens to transformer blocks to the next-token loop
I Built an LLM From Scratch
Build agents, not pipelines
There are only two ways to use LLMs in a computer program: as part of a pipeline, or as an agent. In other words, either you express the control flow of the program in code, or you give a LLM tools and allow it to manage the control flow itself1.
Can LLMs Be Computers? | Percepta
We build a computer inside a transformer — executing arbitrary C programs for millions of steps with exponentially faster inference via 2D attention heads.
What Happens, Exactly, When a Person Talks to an LLM?
A phenomenology of thinking with a model.
Artificial
An LLM is a computer program. We should talk about it like a computer program.
What the AI Wizard taught us about LLM code generation at scale - PostHog
You know what’s boring? Writing integrations. It’s a task you’ll do once, but you always need to do it right, which means carefully reading docs…
Fight fire with pedantry
Over the last two years, I’ve heard a bunch of speculation about how to design a programming language specifically for an LLM. It usually centers around typechecking, formal verifiability, or context engineering. It’s a fun thought experiment, but always felt aimless. First, my experience has been that designing for humans is the best way to design for an LLM, as long as you restrict yourself to text. Second, being in-distribution is so critical that there’s no point unless you’re also training a frontier coding model.
Extensible Software in the age of LLMs | Jeremy Morrell
Solid core + capability-based sandboxes + LLMs = Users with superpowers
LLM-generated skills work, if you generate them afterwards
LLM “skills” are a short explanatory prompt for a particular task, typically bundled with helper scripts. A recent paper showed that while skills are useful to LLMs, LLM-authored skills are not. From the abstract:
Rotating the Space: On LLMs as a Medium for Thought
An essay on LLMs as a cognitive medium
Systems design 3: LLMs and the semantic revolution
Long ago in the 1990s when I was in high school, my chemistry+physics teacher pulled me aside. "Avery, you know how the Internet works, righ...
crawshaw - 2026-02-08
I wrote up my experiences programming with LLMs a bit over a year ago, and updated it for the world of agents eight months ago. A lot has changed since then, so here is an update.
Protecting our FLOSS commons from LLMs — Codeberg News
In Brief: Two motions regarding