Will the next LLM released by OpenAI be worse than GPT-4 at MMLU?
➕
Plus
23
Ṁ1163
Jan 1
16%
chance

The next LLM = the next family of LLM in cases of doubt - an updated version of a previous model doesn't count as a new model for this market

Get
Ṁ1,000
and
S3.00
Sort by:

How big a bump up counts as the next one @firstuserhere? 4.5? 5? A new variant of 4?

Afaik OpenAI has not made a model worse than their previous model before. (gpt-3.5-turbo & text-davinci-003 perform about the same overall so i'm not counting that) and I'm pretty sure ada/babbage/curie/davinci were all released at the same time, and the best of those, davinci, was better than early gpt-3, so that wouldn't count either

© Manifold Markets, Inc.Terms + Mana-only TermsPrivacyRules