Community Blog & Articles

Community Articles

J-Space: Yet Another LLM Mind Reader?

Giving AI Agents 3D Bodies, Real Jobs, and Wallets on three.ws

VKUE: No GPU? Runs Anyway — a 34.7B Reasoner on a Laptop and on Bare CPU

Distillation in 2026 (so far): which frontier models use it and how

KV Caching Explained: Optimizing Transformer Inference Efficiency

Deploy GLM-5.2-FP8 as your open, frontier-level agent

How to visualize any Hugging Face model

Meet Cohere Transcribe Arabic

Can Codex Handle Real-World Data Analysis?

Can Skills Improve Codex’s Data Analysis Capabilities?

Putting DoctoBERT to Work: A Practical Guide

hugging-science

Uncensor any LLM with abliteration

Code a simple RAG from scratch

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond

karina-zadorozhny

Arcee Becomes the First Major American AI Lab to Replace AWS S3 with Hugging Face Private Storage, in a Multi-Million Dollar Commercial Partnership

Why Whisper cuts off Indic transcripts after six seconds

Atom2.7m: Representation-Level Specialization for Arithmetic-Aware Small Language Models

The state-of-the-art in open-source AI for Swiss legal tasks

One Adapter, Both Modalities: Field Notes from Building and Serving a Multimodal Reranker

about 2 hours ago

Newer Models, Same Advantage

Security incident disclosure — July 2026

What building Shippy taught us about building agents

Model Routing Is Simple. Until It Isn’t.

announcementmultimodaltransformers

Welcome Inkling by Thinking Machines

audiospeechbenchmark

Introducing Real World VoiceEQ: Measuring the human quality of voice AI

+9

torchprofileflash

Profiling in PyTorch (Part 3): Attention is all you profile

Data for Agents

vllmtransformersinference

Native-speed vLLM transformers modeling backend

From Hugging Face to Amazon SageMaker Studio in one click

Hugging Face Models on Foundry Managed Compute

guidepartnershipsopen-source-collab

Run AI workloads on any cloud, store on Hugging Face: zero-egress storage with SkyPilot

+1

lerobotrobotics

LeRobot v0.6.0: Imagine, Evaluate, Improve

+5

PRX Part 4: Our Data Strategy

Community Articles

NEW Articles from Team or Enterprise organizations will get promoted to the main section.

J-Space: Yet Another LLM Mind Reader?

Giving AI Agents 3D Bodies, Real Jobs, and Wallets on three.ws

VKUE: No GPU? Runs Anyway — a 34.7B Reasoner on a Laptop and on Bare CPU

Distillation in 2026 (so far): which frontier models use it and how

KV Caching Explained: Optimizing Transformer Inference Efficiency

Deploy GLM-5.2-FP8 as your open, frontier-level agent

How to visualize any Hugging Face model

Meet Cohere Transcribe Arabic

Can Codex Handle Real-World Data Analysis?

Can Skills Improve Codex’s Data Analysis Capabilities?

Putting DoctoBERT to Work: A Practical Guide

hugging-science

Uncensor any LLM with abliteration

Code a simple RAG from scratch

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond

karina-zadorozhny

Arcee Becomes the First Major American AI Lab to Replace AWS S3 with Hugging Face Private Storage, in a Multi-Million Dollar Commercial Partnership

Why Whisper cuts off Indic transcripts after six seconds

Atom2.7m: Representation-Level Specialization for Arithmetic-Aware Small Language Models

The state-of-the-art in open-source AI for Swiss legal tasks

One Adapter, Both Modalities: Field Notes from Building and Serving a Multimodal Reranker

about 2 hours ago

View all articles