News for hackers. Stuff that matters.

A comment on Comparing 60 LLMs with a set of 20 prompts. Parent comment

Re:Comparing 60 LLMs with a set of 20 prompts by rubymamis on Saturday September 09, 2023 @10:39AM (#37445964)
GPT4 seems to me to be the best. Undi95/ReMM-SLERP-L2-13B the runner up (very impressive).
[ Parent | on HN ]
Re:Comparing 60 LLMs with a set of 20 prompts by obiefernandez on Saturday September 09, 2023 @11:40AM (#37446647)
What a name!!
[ Parent | on HN ]
Re:Comparing 60 LLMs with a set of 20 prompts by rootusrootus on Saturday September 09, 2023 @12:25PM (#37447129)
Clearly the prompt construction and initial instructions are critically important here. Without that, the ReMM-SLERP-L2-13B model produces awful results. Blank answers about half the time. For lay users, ChatGPT remains the undisputed winner. Although I do see reasonably good results with the more recent llama-2 70B variations, which are plausibly useful a majority of the time.
[ Parent | on HN ]