March 28, 2024, 1 p.m. | code_your_own_AI

code_your_own_AI www.youtube.com

On day one of the new release of DBRX by @Databricks I did performance tests on causal reasoning and light logic tasks. Here are some of my results after the first 5 to 6 hours of testing.

In summary, it is similar to the performance of ChatGPT (the 3.5 version, not the 4 version), given my data and my tasks in science and causal reasoning.
Your data may vary.


#airesearch
#computerscience
#reasoning

causal chatgpt databricks light logic performance reasoning release results summary tasks test testing tests

Data Engineer

@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York