Can You Run a State-of-the-Art LLM On-Prem for a Reasonable Cost?
2023-07-19
AMD EPYC 9684X Genoa-X Provides HPC Performance
2023-07-19
KumoMTA: High Performance Open-Source Sending MTA to Replace PowerMTA
2023-07-18
Google's answers to factual questions differ person-to-person
2023-07-18
Meta Unveils a More Powerful A.I. and Isn’t Fretting over Who Uses It
2023-07-18
Microsoft to charge $30 per user per month for Copilot for Office
2023-07-18
Finding treacherous encoding permutations with baseperm
2023-07-18
LLama 2 Performance Benchmarks [video]
2023-07-18
Comparison between llama.cpp, AutoGPTQ, ExLlama, etc. perplexities
2023-07-18
Show HN: YouTube Transcript Cleaner and Reader Tool
2023-07-18