Stories by megadragon9

GPT-2 124M checkpoint pre-trained on OpenWebText 27.5B tokens

Self-Improving Harness Is an Experiment Design Problem

Show HN: What 1k Harness Experiments Taught Me About Self-Improving Agents

What 1k Harness Experiments Taught Me About Self-Improving Agents

How a Deep Learning Library Enables Learning

How A Deep Learning Library Enables Learning

Understanding ML: Creating a PyTorch-Inspired Deep Learning Library from Scratch

Show HN: ML Library created by Python+NumPy (trains CNNs to a toy GPT-2)

I Built a Deep Learning Library from Scratch Using Only Python, NumPy and Math

Show HN: From-Scratch ML Library (trains models from CNNs to a toy GPT-2)

Chinese scientist claims world's first gene-edited babies

Do functions that Siri trigger exist in the OS?

Switching from software development in banks to product-oriented tech firms

Service-oriented vs. product-oriented tech firms for new grads

Ask HN: “Unofficial” second year CS student applying for technical internships