惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

D
DataBreaches.Net
罗磊的独立博客
M
MIT News - Artificial intelligence
G
Google Developers Blog
V
V2EX
D
Docker
博客园_首页
The Cloudflare Blog
人人都是产品经理
人人都是产品经理
Y
Y Combinator Blog
WordPress大学
WordPress大学
T
Tailwind CSS Blog
博客园 - 司徒正美
J
Java Code Geeks
L
LangChain Blog
博客园 - 三生石上(FineUI控件)
B
Blog RSS Feed
博客园 - 【当耐特】
小众软件
小众软件
Apple Machine Learning Research
Apple Machine Learning Research
大猫的无限游戏
大猫的无限游戏
P
Proofpoint News Feed
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
博客园 - Franky

Nicholas Carlini

A 2-ply minimax chess engine in 84,688 regular expressions How to win a best paper award (or, an opinionated take on how to do important research) Are large language models worth it? Gate-level emulation of an Intel 4004 in 4004 bytes of C A Python Hardware Description Language DSL Machines of Ruthless Efficiency My Thoughts on the Future of "AI" What my privacy papers (don't) have to say about copyright and generative AI Career Update: Google DeepMind -> Anthropic AI forecasting retrospective: you're (probably) over-confident Letting Language Models Write my Website You should forecast the future of AI How I Use "AI" Why I attack (yet another) Broken Adversarial Example Defense at IEEE S&P 2024 My benchmark for large language models My research idea logfile, 2016-2019 Reading data off an Apple ProFile hard drive with an Arduino Playing chess with large language models Little Bobby <|endoftext|> A ChatGPT clone, in 3000 bytes of C, backed by GPT-2 nicholas.carlini.com Rapid Iteration in Machine Learning Research A Case of Plagarism in Machine Learning Research Multiplexing Circuits on the Game of Life Research Paper Release Checklist A Simple CPU on the Game of Life Improved Logic Gates on Conway's Game of Life Yet Another Space Shooter (In 13kb of JavaScript) Yet Another MOBA (In 13kb of JavaScript)
InstaHide Disappointingly Wins Bell Labs Prize, 2nd Place
2020-12-05 · via Nicholas Carlini
InstaHide (a recent method that claims to give a way to train neural networks while preserving training data …