Compression is prediction(ngrok.com)

611 points by nikolay 2 months ago | 252 comments

An ngrok blog post explaining compression basics and how data compressors and LLMs fundamentally solve the same prediction problem.

RISC-V SBI and the full boot process(popovicu.com)

107 points by snvzz 3 years ago | 22 comments

How to use Linux vsock for fast VM communication(popovicu.com)

71 points by mfrw 11 months ago | 17 comments

How Raw sockets behave differently in macOS and Linux(swagnik.netlify.app)

99 points by adityaathalye 2 years ago | 37 comments

ChatGPT is NOT a LLM – GPT is(vincirufus.com)

14 points by vincirufus 1 year ago | 11 comments

An LLM is a lossy encyclopedia(simonwillison.net)

450 points by tosh 1 year ago | 304 comments

Short blog post by Simon Willison proposing the analogy that an LLM is a lossy encyclopedia, and advising users to supply correct examples rather than rely on recall.