Skip to content
978: A Post-Transformer Architecture Crushes Sudoku (Transformers Solve ~0%) episode artwork

Mar 27, 2026 10 min

978: A Post-Transformer Architecture Crushes Sudoku (Transformers Solve ~0%)

from Super Data Science: ML & AI Podcast with Jon Krohn Hosted by Jon Krohn

A game millions of people solve over morning coffee is exposing a fundamental weakness in today’s most powerful AI models. In this Five-Minute Friday, Jon Krohn breaks down Pathway’s new Sudoku Extreme benchmark, roughly 250,000 of the hardest Sudoku puzzles available and why leading LLMs like o3-mini, DeepSeek-R1, and Claude 3.7 Sonnet scored effectively zero percent, while Pathway’s post-transformer BDH architecture achieved 97.4% accuracy at a fraction of the cost. Listen to the episode to find out what BDH is doing differently, why Sudoku performance matters far beyond puzzles, and what this means for the future of AI reasoning. Additional materials: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠www.superdatascience.com/978⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Interested in sponsoring a SuperDataScience Podcast episode? Email [email protected] for sponsorship information.

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

978: A Post-Transformer Architecture Crushes Sudoku (Transformers Solve ~0%)

0:00 10:39

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of Super Data Science: ML & AI Podcast with Jon Krohn?

This episode is 10 minutes long.

When was this Super Data Science: ML & AI Podcast with Jon Krohn episode published?

This episode was published on March 27, 2026.

Can I download this Super Data Science: ML & AI Podcast with Jon Krohn episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.