Did GPT 5.2 make a breakthrough discovery in theoretical physics?
•
55
Community Blog & Articles
Community Articles
view all
The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator
47
December 17, 2025 
CUGA on Hugging Face: Democratizing Configurable AI Agents
67
December 15, 2025 
New in llama.cpp: Model Management
126
December 11, 2025 
llmfine-tuningopen-source
Codex is Open Sourcing AI models
76
December 11, 2025 
swifthubopen-source
Introducing swift-huggingface: The Complete Swift Client for Hugging Face
43
December 5, 2025 
llmreasoningagents
DeepMath: A lightweight math reasoning Agent with smolagents
40
December 4, 2025 
llmfine-tuningopen-source
HotWe Got Claude to Fine-Tune an Open Source LLM
603
December 4, 2025 
transformersv5community
HotTransformers v5: Simple model definitions powering the AI ecosystem
302
December 1, 2025 
diffusersfluxquantization
Diffusers welcomes FLUX-2
- +4
180
November 25, 2025 
transformerspytorchoptimization
HotContinuous batching from first principles
330
November 25, 2025 
Building Deep Research: How we Achieved State of the Art
35
November 24, 2025 
OVHcloud on Hugging Face Inference Providers 🔥
76
November 24, 2025 
llmexperimentationfine-tuning
20x Faster TRL Fine-tuning with RapidFire AI
27
November 21, 2025 
audiospeechleaderboard
Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks
26
November 21, 2025 NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
Did GPT 5.2 make a breakthrough discovery in theoretical physics?
•
55
FINAL Bench: The Real Bottleneck to AGI Is Self-Correction
•
18
**ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models?**
•
16
Do Bubbles Form When Tens of Thousands of AIs Simulate Capitalism?
•
16
DenseR: Dense Rewards For Free in LLM Reasoning
•
17
I Let a Lobster Run My Jetson: What OpenClaw Taught Me About the Future of Computing
•
13
Introducing Legal RAG Bench
•
10
Uncensor any LLM with abliteration
•
786
Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?
•
7
NVIDIA Nemotron 2 Nano 9B Japanese: 日本のソブリンAIを支える最先端小規模言語モデル
•
23
Kimi K2.5: Still Worth It After Two Weeks?
•
6
Follow the White Rabbit: Using Embeddings So You Never Get Lost in Translation
•
6
Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR
•
82
Code a simple RAG from scratch
•
301
Mastering Tensor Dimensions in Transformers
•
142
Introducing NVIDIA Cosmos Policy for Advanced Robot Control
•
43
GEM Image: Building an AI That Actually Gets Educational Diagrams Right
•
4
MAEB: Evaluating Audio Embeddings at Scale
•
4
Introduction to State Space Models (SSM)
•
211
Simplifying Alignment: From RLHF to Direct Preference Optimization (DPO)
•
46