字号

Surprisal – a language identifier in ~250 lines of C. No ML,no training

github.com · 海外项目
1HN 得分
昨天出现时间

项目说明

I made a text/language identifier today, in a single C file, with no ML.It classifies a text by checking which reference text a hand-rolled greedy LZ77 compressor finds least surprising. Each class is

标签

数据
访问项目

相关项目

nv-rs
slaterain/nv-rs
Omnesis – A private knowledge layer for ChatGPT and other agents
omnesis.dev
Our space game has a built-in RISC-V emulator that runs Linux
againstallodds.games
Burning Man for Agents
burning-tokens.transitivebullsh.it
RemoveMacAI
omlahore/RemoveMacAI
Every number in a tiny GPT, from one forward pass to one step of RLHF
llm.manogya.dev

数据来源:Hacker News · 收录于 2026-10-14