Là một dự án mã nguồn mở, pathwaycom/bdh đã đạt 3.6k sao trên GitHub, ngôn ngữ Python. BDH (Dragon Hatchling) – Architecture and Code
Tóm tắt dựng từ metadata GitHub của chính dự án — chưa có bài review TopGit. Trang sẽ tự động cập nhật khi bài review đầy đủ được xuất bản.
VÌ SAO CHƯA CÓ REVIEW
TopGit viết bài đầy đủ cho repo có nhiều sao nhất và được yêu cầu nhiều nhất. Trang này là snapshot trong thời gian chờ — xem README gốc ở tab READ ME.
Bridging the Gap Between Transformers and the Brain
BDH (Dragon Hatchling) is a biologically inspired large language model architecture that connects principles of deep learning with the foundations of neuroscience. Developed by researchers at Pathway, BDH provides a theoretical and practical framework for understanding the emergence of reasoning and generalization in artificial systems.
This repository contains the official implementation from the paper:
A. Kosowski, P. Uznański, J. Chorowski, Z. Stamirowska, M. Bartoszkiewicz.The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain, arXiv (2025).
Overview
BDH represents a scale-free, locally interacting network of neurons capable of intrinsic reasoning dynamics. BDH scales like a Transformer on performance benchmarks—yet retains full interpretability and theoretical grounding in the fine-grained dynamics of neuron interactions.
Locally interacting neuron particles with excitatory/inhibitory dynamics
Hebbian working memory based on synaptic plasticity, displaying monosemanticity
GPU-friendly state-space formulation for efficient implementation
Interpretable activations that are sparse and positive
BDH formalizes a bridge between neural computation and machine-based language understanding. It shows how macro reasoning behavior in large AI models emerges from micro-level neuron dynamics, guided by principles of graph theory and local computation.
Empirically, BDH matches GPT-2–scale Transformers across language and translation tasks at equivalent parameter scales (10M–1B).
Architecture
Relation to Transformers
BDH and the Transformer share attention-inspired computation; however, BDH’s graph-based architecture makes its attention emerge naturally from neuron-level interactions, reflecting attention as seen in biological systems.
Scaling Laws
BDH follows Transformer-like scaling laws, maintaining parameter efficiency while achieving interpretability at any scale.
Latest research update: Sudoku Benchmark
Note: The Sudoku Extreme result refers to Pathway’s internal BDH implementation, not to the current open-source repository. This repository contains the implementation of the baseline variant as described in our public paper and does not reproduce the 97.4% benchmark result out of the box. See the dedicated Extreme Sudoku research blog post for additional benchmark context and the reported results.
On Sudoku Extreme, BDH reaches 97.4% accuracy across roughly 250,000 difficult puzzles, without chain-of-thought, solution backtracking, or external tool use, while leading LLMs struggle to perform on the benchmark at all.
Language is not enough for intelligence. Transformers process information token by token with limited internal state, which makes search-heavy, non-linguistic reasoning tasks like Sudoku awkward. BDH uses a larger latent reasoning space with intrinsic memory that supports learning and adaptation during use.
We believe that the future of AI will belong to systems that can reason natively across domains, that can hold multiple possibilities in a rich latent space, and that can converge on solutions without needing to verbalize every step. BDH is our answer to that challenge. It is designed to be a universal reasoning system that can speak our language without being trapped inside it. And yes, it solves Sudoku.
Read more: Post-transformers: Sudoku Bench
Performance Comparison
Model
Sudoku Extreme Accuracy
Relative Cost
Pathway BDH
97.4%
10× lower, No chain-of-thought
Leading LLMs (O3-mini, DeepSeek R1, Claude 3.7 8K)
~0%
High (chain-of-thought)
Table 1: Performance comparison on extreme Sudoku benchmarks (~250,000 difficult puzzles). Source: Pathway internal data and https://arxiv.org/pdf/2506.21734 for the Leading LLMs’ accuracy score. Pathway’s approach reflects top-1 accuracy and does not rely on chain-of-thought nor solution backtracking.
Installation and Training
# install dependencies
pip install -r requirements.txt
# train BDH on a toy dataset
python train.py
Learn and Discuss
Watch the SuperDataScience podcast ▶️ Dragon Hatchling: The Missing Link Between Transformers and the Brain (72 min.) featuring Adrian Kosowski in conversation with Jon Krohn, unpacking BDH’s neuron-level architecture and sparse reasoning dynamics.
Read about BDH in
Forbes,
Semafor,
The Turing Post,
Quantum Zeitgeist,
Golem,
and elsewhere in the media.
Discuss and share the BDH paper on:
Hugging Face Papers,
Alphaxiv,
and EmergentMind.
We thank Andrej Karpathy for the nanoGPT code and the tiny Shapespeare dataset used in this demonstration.
BDH research stands at the intersection of AI architecture, biological learning models, and theoretical computer science—an effort to map the equations of reasoning between artificial and biological intelligence.
Trang TopGit này là một snapshot — tab "Readme" hiển thị nguyên văn README của repo (đã bỏ link, giữ ảnh). Repo GitHub ở github.com/pathwaycom/bdh là nguồn chính thức.
pathwaycom/bdh có bao nhiêu sao?
pathwaycom/bdh có 3.6k sao GitHub — tải lại trang để xem số mới nhất, hoặc xem trực tiếp github.com/pathwaycom/bdh. TopGit phản chiếu số sao của GitHub nhưng không cam kết đến từng phút.
pathwaycom/bdh có phải mã nguồn mở không?
Có — pathwaycom/bdh phát hành theo license MIT, nghĩa là mã nguồn mở để đọc, fork và (tùy license) tái sử dụng. Mã: github.com/pathwaycom/bdh.
pathwaycom/bdh có website riêng không?
TopGit chưa ghi nhận URL trang chủ cho pathwaycom/bdh. Phần README ở tab phía trên thường có link demo, hoặc xem mô tả GitHub của repo.
pathwaycom/bdh là gì?
pathwaycom/bdh (pathwaycom/bdh) là dự án Python trên GitHub. Theo mô tả gốc: BDH (Dragon Hatchling) – Architecture and Code
Đọc đầy đủ README ở tab phía trên.
Muốn nghe thêm một ý kiến về bdh?
Hỏi một AI đọc được trang này — một cú bấm là có ngay nhận định về bdh.