Show HN: Commit code into a neural network, see what it remembers (browser demo)
Smaller network = more errors = more fun. Try --hidden 16 on text, or paste your own image
以下正文同步自 Hacker News 最新，版权归原站所有，已转换为易读排版。
commit log
Smaller network = more errors = more fun. Try --hidden 16 on text, or paste your own image
Instead of storing your files as bytes, lgit trains a small neural network to memorize them. Each commit is a training run: the network learns to map positional encodings to your data, byte by byte for code or pixel by pixel for images. Checkout is inference: the network reconstructs what it can from its weights
The network uses Fourier positional encoding, ReLU hidden layers, and an Adam optimizer. For text, it outputs a probability distribution over 256 byte values. For images, it predicts RGB values directly. A small network compresses aggressively and hallucinates. A larger one memorizes perfectly but defeats the point
正文由 探How 从来源站点 RSS 同步，内容未经改写；遇到排版缺失或需要图片、视频时请以原文为准。