Solving Sudoku reasoning via Energy Geometric models
Details
- External ID
- 46986604
- Source
- HN
- Company
- —
- Product
- Solving Sudoku reasoning via Energy Geometric models
- Website domain
- davisgeometric.com
- Launched
- Feb. 12, 2026
- Cohort
- —
- Upvotes
- 18
- Upvotes percentile
- 0.6711590296495957
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
We were genuinely impressed by Yann LeCun’s recent announcement about his Sudoku solver based on Energy-Based Models here: https://logicalintelligence.com/yann-lecunSo we (a software engineer and prodigy mathematician) worked in the weekend to see if we can beat it and we did!If Kona solves puzzles in 313 milliseconds, we currently solve 270,000 puzzles per second!We do not know the internal mechanics behind Logical Intelligence’s system, but we are happy to share ours in the webpage there is a full description, code and also a paper published.Why people are obsessed with Sudoku: we think is because being a CSP, it can solve some serious business problems such as work scheduling, resource allocations and logistic optimization.For any questions reach me out to: [email protected].
Enrichment
- Theme
- indie puzzle games and learning toys
- Vertical
- Horizontal
- Function
- Observability & eval
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- sudoku solver using energy geometric models
- Manually corrected
- False
Could you build this?
No Developing novel Energy-Based Geometric Models for constraint-satisfaction reasoning like Sudoku requires advanced academic mathematics and machine learning research.
What it would actually take: This project requires designing non-standard energy functions, manifold optimization routines, and neural network architectures based on geometric deep learning and statistical physics. Implementation entails custom loss functions, differentiable relaxation of discrete constraints, and specialized gradient/energy descent algorithms in PyTorch or JAX. It requires an AI researcher or mathematical physicist specializing in energy-based models.
Discussion
4 comments analyzed.
Competitors mentioned: SAT solver
Concerns raised: Unclear why manifolds and wavefronts approach chosen for sudoku solving, Product image appears AI-generated, Suspicious patent and publication timeline concentrated in late 2025, Inactive GitHub repository until December 2025 with unexplained code, Founder credibility concerns - age inconsistency with claimed experience
Competitors
Other products that read as similar to this one — 90 launches clear the similarity bar, closest 8 shown.
Attention rank: #38 of 91 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 106 days after the earliest competitor.
- Pencil Puzzle Bench · hn · 2026-03-03 · 5 upvotes · similarity 0.53
- A puzzle I couldn't solve for a year · hn · 2026-08-21 · 18 upvotes · similarity 0.52
- Dozenal · hn · 2026-07-27 · 16 upvotes · similarity 0.49
- FuseCells · hn · 2025-12-06 · 37 upvotes · similarity 0.44
- Kyomu · hn · 2026-04-13 · 5 upvotes · similarity 0.43
- FuseCells · hn · 2025-12-31 · 6 upvotes · similarity 0.43
- PuzzleCrackerAI · ph · 2026-09-29 · 1 upvotes · similarity 0.43
- sudoku-graph-coloring · github · 2026-09-20 · 11 upvotes · similarity 0.43
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a observability & eval tool for Media & entertainment yet.