Can LLMs Be Computers? | Percepta

Artificial

An LLM is a computer program. We should talk about it like a computer program.

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

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.

Extensible Software in the age of LLMs | Jeremy Morrell

Solid core + capability-based sandboxes + LLMs = Users with superpowers

Modern GPU Programming For MLSys — Modern GPU Programming For MLSys

Machine learning systems sit at the heart of modern AI workloads. In these systems, performance often comes down to the quality of a small number of GPU kernels. Attention kernels, LLM prefill and decode kernels, low-precision block-scaled GEMMs, fused MoE layers, and other large fused kernels all directly shape end-to-end speed in both training and serving.

Fast and Hard Code

People pick languages differently with LLMs.

MemGPT

Memory-GPT (MemGPT) - Towards LLMs as Operating Systems - Teach LLMs to manage their own memory for unbounded context!

Why Futhark?

A high-performance and high-level purely functional data-parallel array programming language that can execute on the GPU and CPU.

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.

We Don't Understand Neural Networks At The Algorithmic Level

The largest ongoing debate about AI is “Are Large Language Models (LLMs) intelligent?” That makes sense, at least: the evidence is ambiguous and the stakes a...

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…

Self-Instruct: Aligning Language Models with Self-Generated Instructions

Large "instruction-tuned" language models (i.e., finetuned to respond to instructions) have demonstrated a remarkable ability to generalize zero-shot to new tasks. Nevertheless, they depend...

Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models

Sparse Mixture-of-Experts (MoE) is a neural architecture design that can be utilized to add learnable parameters to Large Language Models (LLMs) without increasing inference cost. Instruction tuning is a technique for training LLMs to follow instructions. We advocate combining these two approaches, as we find that MoE models benefit more from instruction tuning than dense models. In particular, we conduct empirical studies across three experimental setups: (i) Direct finetuning on individual downstream tasks devoid of instruction tuning; (ii) Instructiontuning followed by in-context few-shot or zero-shot generalization on downstream tasks; and (iii) Instruction tuning supplemented by further finetuning on individual downstream tasks. In the first scenario, MoE models overall underperform dense models of identical computational capacity. This narrative, however, dramatically changes with the introduction of instruction tuning (second and third scenario), used independently or in conjunction with task-specific finetuning. Our most powerful model, FLAN-MOE-32B, surpasses the performance of FLAN-PALM-62B on four benchmark tasks, while using only a third of the FLOPs. The advancements embodied byFLAN-MOE inspire a reevaluation of the design principles of large-scale, high-performance language models in the framework of task-agnostic learning.

Modular: The Claude C Compiler: What It Reveals About the Future of Software

Compilers occupy a special place in computer science. They're a canonical course in computer science education. Building one is a rite of passage. It forces you to confront how software actually works, by examining languages, abstractions, hardware, and the boundary between human intent and machine execution.

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...