Will any LLM have roughly GPT-3-level losses with a context window of at least 50,000 tokens before April of 2024?
21
139
Ṁ860Ṁ410
Apr 1
80%
chance
1D
1W
1M
ALL
Get Ṁ1,000 play money
Related questions
Sort by:
@IsaacKing Doesn't Claude 2 fit this description? Performs better than GPT-3 on pretty much every task, and has a long enough context length?
I think this question is ill-posed and you shouldn't compare losses between models. It is technically well-defined(i.e. somebody with access to OpenAI's dataset could score the prediction accuracy of any model), but in practice people use standardized benchmarks like the recent GPT-4 release. And the actual loss numbers you see reported in charts won't be comparable.
I think you should N/A this market as not meaningful, or specify some benchmarks instead.
Related questions
Which company's model will capture the largest share of the enterprise LLM market by EOY 2025?
Will Google Home Assistant have LLM integration by March 31, 2024? [1000M subsity]
3% chance
Will I release the source code for at least one new personal project with major contribution of a LLM tool by 2024.Q1?
23% chance
Will an LLM or some form of AI system be found out to perform arbitrage on Manifolds and be profitable before Q2 2024?
42% chance