Into AI

Into AI

Share this post

Into AI
Into AI
DeepSeek-R1 & OpenAI's o1 Aren't Still As Intelligent As Portrayed.
Copy link
Facebook
Email
Notes
More

DeepSeek-R1 & OpenAI's o1 Aren't Still As Intelligent As Portrayed.

Here are the results of testing R1 and o1 on the toughest mathematical questions known to humans.

Dr. Ashish Bamania's avatar
Dr. Ashish Bamania
Jan 30, 2025
∙ Paid
12

Share this post

Into AI
Into AI
DeepSeek-R1 & OpenAI's o1 Aren't Still As Intelligent As Portrayed.
Copy link
Facebook
Email
Notes
More
5
4
Share
A wide illustration featuring a whale crafted in a woolen style, made entirely from yarn or wool with detailed knitting patterns. Surrounding the whale are mathematical elements, including floating equations, geometric shapes, and numerical symbols, all integrated into the woolen texture. The background features a knitted fabric texture with mathematical formulas subtly woven into it, enhancing the handmade yet intellectual aesthetic. The image is set in a 2:1 aspect ratio, giving a panoramic view of the woolen whale swimming through a mathematical, knitted sea.
Image generated with DALL-E 3

There’s a lot of enthusiasm (and fear) around AGI approaching soon.

The release of OpenAI’s o1 led to a big boost in this conviction.

Into AI is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.

And now, we have DeepSeek-R1, a powerful open-source reasoning model that beats o1 on many benchmarks, further fuelling this conviction train.

Keep reading with a 7-day free trial

Subscribe to Into AI to keep reading this post and get 7 days of free access to the full post archives.

Already a paid subscriber? Sign in
© 2025 Dr. Ashish Bamania
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share

Copy link
Facebook
Email
Notes
More