2023-09-09 Hacker News Top Articles and Its Summaries
1. Asking 60 LLMs a set of 20 questions Total comment counts : 61 Summary The author developed a script to test around 60 models with prompts related to reasoning, instruction following, and creativity. The script stored the answers in a SQLite database, and the raw results are available to view. Top 1 Comment Summary The article discusses a generic harness that can be used to run benchmarks across various language models....