Meta LLM Compiler: neural optimizer and disassembler(twitter.com)230 points by foobazgt 2 years ago | 92 comments
Cerebras launches inference for Llama 3.1; benchmarked at 1846 tokens/s on 8B(twitter.com)63 points by _micah_h 2 years ago | 24 comments
OpenAI starts rolling out new voice mode(twitter.com)17 points by doubtfuluser 2 years ago | 9 comments
Backdoor attempt on Exolabs GitHub repo through an innocent looking PR(twitter.com)124 points by amrrs 1 year ago | 74 comments
Figma AI looks rather trained on existing apps(twitter.com)13 points by tambourine_man 2 years ago | 0 comments
Nvidia and its partners built a system to bypass U.S. export restrictions(twitter.com)301 points by mgh2 2 years ago | 168 comments
