Stories by paladin314159

A Tale of Two Production Bugs (Part 2)

A Tale of Two Production Bugs (Part 1)

Structured Outputs for LLMs

Distributed Game Servers in KFChess

Speculative Decoding in LLM Inference

Triton Language

Linear Representations and Superposition

Reflections on Using Claude Code

Quantization-Aware Distillation

LLM Quantization and NVFP4

Sparse File LRU Cache

Observations from Using Claude Code

Why Sam Altman was booted from OpenAI, according to new testimony

Torchcomms: A modern PyTorch communications API

The Fundamental Forces of Scale

How Jensen Huang's Nvidia is powering the A.I. revolution

A Designer's Guide to using AI to turbocharge creativity

Amplitude Analytics, CDP, and Experiment: $49/month

Ask Amplitude

1 2