Why MMAP in llama.cpp hides true memory usage(twitter.com)95 points by flurly 3 years ago | 69 comments
GPT-4 “discovered” the same sorting algorithm as AlphaDev by removing “mov S P”(twitter.com)181 points by machdiamonds 3 years ago | 58 comments
Weird GPT-4 behavior for the specific string “ davidjl”(twitter.com)233 points by goranmoomin 3 years ago | 190 comments
Llama.cpp can do 40 tok/s on M2 Max, 0% CPU usage, using all 38 GPU cores(twitter.com)40 points by samwillis 3 years ago | 9 comments
My total comp for creating GitHub Copilot(twitter.com)108 points by FlamingMoe 3 years ago | 60 comments
