Stories by niklas-e

Forward Self Models

Tapered Language Models

Everything is logarithms

Deactivated Slack Profile Generator

Explaining Attention with Program Synthesis

FFI in Miri at 8000 segfaults per second [video]

Sparsely gated tiny linear experts

Robotics Has a Stiffness Problem

Training-Free Single-Image Diffusion Models

Simple input–output dependencies explain neuronal activity

Self Teaching Autoencoder

Distance Marching for Generative Modeling

Int a = 5; a = a++ + ++a; a =? (2011)

A Theory of Generalization in Deep Learning

Show HN: Zerminal – a terminal-first Zed fork for AI coding agents

Neural similarity predicts whether strangers become friends

Ask HN: Is it just me or is Claude Code getting worse?

What Happened to Claude Code

Generation Is Required for Data-Efficient Perception

Flow Map Learning via Nongradient Vector Flow [pdf]

1 2 3 4 5 6 7 8 9 10