Memory-GPT (MemGPT) - Towards LLMs as Operating Systems - Teach LLMs to manage their own memory for unbounded context!
Extensible Software in the age of LLMs | Jeremy Morrell
Solid core + capability-based sandboxes + LLMs = Users with superpowers
Oxmgr — Rust Process Manager
42× faster crash recovery, 20× lower memory than PM2. Written in Rust.
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.
Magicoder: Empowering Code Generation with OSS-Instruct
We introduce Magicoder, a series of fully open-source (code, weights, and data) Large Language Models (LLMs) for code that significantly closes the gap with top code models while having no more...
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
Context Rot: How Increasing Input Tokens Impacts LLM Performance
Claude Sonnet 4, GPT-4.1, Qwen3-32B, and Gemini 2.5 Flash on Repeated Words Task
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.
Rotating the Space: On LLMs as a Medium for Thought
An essay on LLMs as a cognitive medium
Guardian Angels: LLM Personalization for Productivity and Security
I propose an approach for highly personalized LLMs, for near-future productivity gains and personal info/cybersecurity against increasingly powerful LLMs: they should, in the spirit of uploading, try to emulate the user’s values and preferences in order to amplify the principal—not replace them. I discuss a package of techniques and proposals to accomplish such ‘guardian angels’; dynamic evaluation of LLMs combined with active learning and elicitation and heavy inner-monologue search/data-augmentation.
Forking is Cool, or: A Unix Shell in Zig, or: Dave Learns How to Fork - ratfactor
In this article, I make a real, working interactive shell written in Zig. Though essentially a toy, it demonstrates the incredible elegance of the fork() system call and is an example of what can be done with absolutely no runtime memory allocations.
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...
Artificial
An LLM is a computer program. We should talk about it like a computer program.
Account delegation for atproto: orgs, aliases, alts and more - Nel Ramblings
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.
Augment
A collection of essays on the future of personal computing — specifically, on the kind we’d like to see more of in the future, and the ideas that might help us get there.
