The Oath

Gary Marcus

Rank 11 of 47
|
Score 83
Gary Marcus
@GaryMarcus
--
@muddsicle I’d like to see 3.5 included and with all available measures, for sure
4/12/2024, 2:15:40 AM
X
In reply to:
Austin Mudd
@muddsicle
·
661d
@GaryMarcus Why leave 3.5 turbo off?
Gary Marcus
@GaryMarcus
·
661d
What happens when you plot GPT-2, 3, 4, and Turbo side-by-side?

Below I have plotted one common measure, MMLU, where there are easy to find data going back to GPT-2. (There may be others with data going back that far; this is just a first quick attempt.)


What I see is an…
Gary Marcus
@GaryMarcus
·
661d
Could we see GPT 3 and 3.5 and GPT 4 on the same plot? And Gemini Pro 1.5 and Claude Opus?

The statement is a technical request for the inclusion of a specific AI model version in a performance comparison chart. It is part of a specialized conversation about AI model performance and does not address broader societal issues.

FacebookInstagramTwitterYouTube

© 2023-2024 The Oath, All rights reserved.