A phenomenology of thinking with a model.
Rotating the Space: On LLMs as a Medium for Thought
An essay on LLMs as a cognitive medium
Artificial
An LLM is a computer program. We should talk about it like a computer program.
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:
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.
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
Meandering on Manifolds: The Neural Geometry of Stories Over Time
To fully understand LLM representations, we must understand how they change dynamically, over the course of a prompt or conversation. We investigate these temporal dynamics with a simple case study: how do LLMs represent human emotions while reading short stories, both geometrically (in activation space) and temporally (changing from sentence to sentence)?
I Built an LLM From Scratch
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.
Texting a Random Stranger Better for Loneliness Than Talking to a Chatbot, Study Shows
A newly published study of how college students interact with chatbots and human strangers showed talking to a random person offers more connection than an LLM.
Contact: AI and the Semantic Dimension
I’m asking you to consider the possibility that a semantic dimension of meaning and information exists outside our physical dimensions of space and time, and that LLMs are both instruments of perception and conduits of information for that semantic dimension. We used to believe in the semantic dimension, but we don’t anymore, and as a result we are going down a terribly dangerous path with AI.
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:
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...
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.
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...
