news Reading Today’s Headlines Through AI: A Real-Time Audit of Six Commercial Chatbots In a new study, scholars measured how accurately popular AI chatbots answered questions about the emerging news and found...
news Today's AI Talks Like “Nobody.” New Research Gives It Real Personality. PsychAdapter lets researchers dial in on personality traits, age, and mental health characteristics to generate text that sounds like real...
Related News PsychAdapter lets researchers dial in on personality traits, age, and mental health characteristics to generate text that sounds like real individuals, opening the door to training simulations and...
DeepSeek released V4 today. Two MoE checkpoints are on the Hub: DeepSeek-V4-Pro at 1.6T total parameters with 49B active, and DeepSeek-V4-Flash at 284B total with 13B active. Both have a 1M-token context window. The...
OpenAI released Privacy Filter on the Hub this week: an open-source personally-identifiable information (PII) detector that labels text across eight categories in a single forward pass over a 128k context. Model card...
NVIDIA Nemotron 3 Nano Omni is a new omni-modal understanding model built for real-world document analysis, multiple image reasoning, automatic speech recognition, long audio-video understanding, agentic computer use,...
We're thrilled to share that DeepInfra is now a supported Inference Provider on the Hugging Face Hub! DeepInfra joins our growing ecosystem, enhancing the breadth and capabilities of serverless inference directly on the...
An in-depth technical walkthrough of data engineering, pre-training, supervised fine-tuning, and reinforcement learning behind the Granite 4.1 LLMs. Authors: Granite Team, IBM TL;DR — Granite 4.1 is a family of dense,...
"When a measure becomes a target, it ceases to be a good measure." (Goodhart’s Law) TLDR: Appen Inc. and DataoceanAI have provided high-quality English ASR datasets covering scripted and conversational speech over...
PipelineRL uses vLLM as the inference engine for rollout generation. The inference engine samples tokens and returns token logprobs; the trainer uses those logprobs to compute policy ratios, KL, clip rate, entropy, and...
For a long time, "scaling" in foundation models mostly meant one thing: spend more compute on pre-training and capabilities rise. That intuition was supported by empirical work such as Kaplan et al. (2020), which...
TL;DR: we explain how to separate CPU and GPU workloads to get a massive performance boost for inference. This is the second post in a series on efficient LLM inference. The first post covered continuous batching from...
TL;DR: Two new Apache 2.0 multilingual embedding models built on ModernBERT — a 97M-parameter compact model that beats every open sub-100M multilingual embedder on MTEB Multilingual Retrieval (60.3), and a 311M...
PaddleOCR 3.5 brings OCR and document parsing tasks closer to the Hugging Face ecosystem. With this release, supported PaddleOCR models can run with Hugging Face Transformers as an inference backend by setting: engine=...
TL;DR Today I'm releasing six new Sentence Transformers CrossEncoder rerankers, state-of-the-art at their respective sizes, built on top of the Ettin ModernBERT encoders, together with the data and full training recipe...
???? Models: https://huggingface.co/collections/allenai/olmoearth???? Tech Report: https://allenai.org/papers/olmoearthv11???? Code: https://github.com/allenai/olmoearthpretrain We released OlmoEarth (v1) in November...
When a field evolves quickly, its vocabulary often evolves faster than its shared understanding. Terms start to blur, get reused in different contexts, or become shorthand for ideas that are never fully explained. We...
TL;DR, because you have models to train and we respect that: Async RL has a dirty secret: every step, the trainer has to ship the whole model to the inference engine. For a 7B in bf16 that is 14 GB. For a frontier 1T...
After building your Reachy Mini, you'll install the conversation app and start talking to it. Until now, you had to send your audio to a server. But not anymore. Today we'll walk you through running the whole stack...
What you cannot profile, you cannot optimize. Whether you are trying to squeeze more tokens per second out of a Large Language Model (LLM), shave milliseconds off inference, or just understand why your training loop...
Guides have aided humanity throughout history. Prehistoric civilizations understood that the sun and the moon could be used to navigate vast distances on land and the high seas. Over time, various journeys facilitated...
Mellum2 is a 12B-parameter Mixture-of-Experts model trained from scratch on natural language and code. The model activates only 2.5B parameters per token, making it efficient for high-throughput, low-latency inference...
Last March, we released Holo3, our state-of-the-art computer-use model. Adoption was immediate. Developers, enterprises, and partners started deploying Holo3 across a wide range of workflows, from browser automation and...
Reachy Mini no longer has to look out the window to tell you the weather The Reachy Mini conversation app can now use tools hosted in public Hugging Face Spaces, called over MCP. You can give your robot a new ability,...
Using Rejection Pairs From Your Model's Own Failures In April, we released DharmaOCR, our specialized structured OCR model ( available on Hugging Face ) along with a paper detailing the methodology behind it and a...
hf is the official command-line entrypoint to the Hugging Face Hub. Anything you can do on the Hub from the Python SDK, you can do from your terminal: download and upload models, datasets and Spaces; create and manage...
The last two years have seen NVIDIA's content safety stack grow from a focused English text classifier into a family of specialized models—each extending coverage to new modalities, languages, and inference modes...
OpenEnv is a tool for creating an agentic execution environment like terminals, browsers, or anything an agent can interact with. And today, we’re excited to announce that OpenEnv is becoming even more open, to make the...
If you have a GitHub repository and you have GitHub Actions enabled, you probably use GitHub-hosted runners for CI. That is the default for many projects because it is simple: add a workflow, write runs-on:...
An agent built a 3D Paris gallery from two Hugging Face Spaces. I asked a coding agent to build a beautiful website showcasing the monuments of Paris as 3D Gaussian splats. I never opened an image generator. I never...
All co-authors listed below Today, we are releasing North Mini Code, a 30B-parameter Mixture-of-Experts model with 3B active parameters with powerful agentic coding capabilities, available on Hugging Face under the...
In the first part of this series "Profiling in PyTorch", we used torch.add(torch.matmul(x, w), b) to learn how to read PyTorch profiler traces. We also discussed several other topics that came our way - the CPU dispatch...
???? Code: https://github.com/allenai/olmo-eval While you're building an LLM, you evaluate it over and over across many interventions. Every adjustment to its data, architecture, or hyperparameters — and every step up...
2026-04-16 7 min read Every agent needs search: Coding agents search millions of files across repos, or support agents search customer tickets and internal docs. The use cases are different, but the underlying problem...
2026-04-16 8 min read An agent needs to be powered by a large language model. A few weeks ago, we announced that Workers AI is officially entering the arena for hosting large open-source models like Moonshotâs Kimi...
2026-04-16 5 min read AI models are changing quickly: the best model to use for agentic coding today might in three months be a completely different model from a different provider. On top of this, real-world use cases...