Exploring OpenAI's o1-preview and o1-mini

09/27/24 • 42 min

OpenAI recently released its o1-preview, which they claim outperforms GPT-4o on a number of benchmarks. These models are designed to think more before answering and handle complex tasks better than their other models, especially science and math questions.
We take a closer look at their latest crop of o1 models, and we also highlight some research our team did to see how they stack up against Claude Sonnet 3.5--using a real world use case.
Read it on our blog: https://arize.com/blog/exploring-openai-o1-preview-and-o1-mini

To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

09/27/24 • 42 min

Deep Papers - Exploring OpenAI's o1-preview and o1-mini

Transcript

John Gilhuly: Hello, everybody joining in here. How's it going? We'll give it a couple of minutes as people filter their way in, but I get started a minute or two.

Aman Khan: Yeah, this should be an interesting one. I feel like I'm like, I definitely think more, more folks joining us on the interesting as well as we go through.

John Gilhuly: Yeah, definitely.

Can also give a little bit of quick intros, as folks are sort of ma

Generate a badge

Get a badge for your website that links back to this episode

Select type & size

Copy