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. And in that case, what are you doing designing a programming language?
Artificial
An LLM is a computer program. We should talk about it like a computer program.
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...
LLMs reward expertise
In the 2010s, if you had technical gaps (say, you couldn’t write CSS), you had to either rely on a skilled colleague or just hope that the answer to your exact problem was out there on the internet. Today, everyone can write sort-of-okay CSS by delegating the task to an LLM. LLMs make everybody into a generalist.
Rotating the Space: On LLMs as a Medium for Thought
An essay on LLMs as a cognitive medium
How To Write With An LLM
Two rules keep an LLM from pasteurizing your writing: never take a word it suggests, and never let it encourage you. Then hand it all the tedious work.
How to write it like you told it
What do you say to someone who wants to write but struggles with writing and is tempted to use an LLM-based chatbot?
What Happens, Exactly, When a Person Talks to an LLM?
A phenomenology of thinking with a model.
I Built an LLM From Scratch
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…
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.
Giving LLMs a personality is just good engineering
AI skeptics often argue that current AI systems shouldn’t be so human-like. The idea - most recently expressed in this opinion piece by Nathan Beacom - is that language models should explicitly be tools, like calculators or search engines. Although they can pretend to be people, they shouldn’t, because it encourages users to overestimate AI capabilities and (at worst) slip into AI psychosis. Here’s a representative paragraph from the piece:
How LLMs Actually Work
A from-the-ground-up walkthrough of how modern LLMs work, from tokens to transformer blocks to the next-token loop
Scaling Laws Across Model Architectures: A Comparative Analysis of...
The scaling of large language models (LLMs) is a critical research area for the efficiency and effectiveness of model training and deployment. Our work investigates the transferability and...
Extensible Software in the age of LLMs | Jeremy Morrell
Solid core + capability-based sandboxes + LLMs = Users with superpowers
