Run 70B LLM Inference on a Single 4GB GPU with This New Technique(ai.gopubby.com)80 points by gardenfelder 2 years ago | 39 comments
How Hackerman would create an image just by typing 0 and 1 – deep dive into GIF(medium.com)113 points by happybits 2 years ago | 37 comments
Introducing Exploit Observer — More than Shodan Exploits, Less than Vulners(blog.arpsyndicate.io)42 points by g147 2 years ago | 6 comments
Architecture Patterns: The Circuit-Breaker(lab.scub.net)64 points by kiyanwang 2 years ago | 11 comments