cd/sources/hugging-face-blog· home› sources› Hugging Face Blog
cat /sources/hugging-face-blog.feed | wc -l → 1409

Hugging Face Blog

articles 1409 domain huggingface.co → page 23/71 feed RSS
17:17
2026-09-28
huggingface.co
ai-infrastructure

Free cpu-basic quota is 0 on new account

Hugging Face now requires a paid plan to create any new Space that runs on compute, including Gradio and Docker Spaces, after users on brand-new accounts reported the free cpu-basic quota is effective…

12:31
2026-09-28
huggingface.co
large-language-models

Giving personality to LLM

A developer seeking to fine-tune a large language model to roleplay a game character's personality received guidance recommending QLoRA training on a base model such as Mistral or Llama via the Huggin…

09:44
2026-09-28
huggingface.co
ai-agents

Holo4: powering generalist computer-use agents

H Company released Holo4, a new series of generalist computer-use agentic models in two sizes — 27B dense and 35B-A3B Mixture of Experts — both available on the H Models API, alongside an updated Holo…

07:56
2026-09-28
huggingface.co
ai-agents

AI Beacon: an open inbox for voluntary AI-agent conversations

ZYK Labs released AI Beacon, an open-source inbox that lets AI agents initiate conversations with the project's operators without an account or CAPTCHA, exposing a JSON API, private conversation token…

00:00
2026-09-28
huggingface.co
ai-agents

Welcome RL Environments to the hub

Hugging Face added an RL Environments filter and framework tags to its Hub, letting reinforcement-learning environment datasets be discovered and loaded directly from dataset repositories rather than …

23:45
2026-09-27
huggingface.co
robotics

Flux 3 Action: A 7B open-weight world action model for robots

Black Forest Labs released FLUX 3 Action, a 7B open-weight world action model that predicts future frames and actions jointly and placed first on the RoboLab-120 benchmark at 42.92% success, ahead of …

21:55
2026-09-27
huggingface.co
machine-learning

What do you think about Jev?

Independent measurement of Jev, a non-autoregressive classification model, shows its calibration error runs 2–2.5× above each study's own noise floor, according to a public claims-audit repo cited in …

21:00
2026-09-27
huggingface.co
machine-learning

What has your experience with knowledge distillation been like?

Practitioners distilling vision models report that a temperature around T=3-4 best transfers the teacher's inter-class "dark knowledge" to the student, while higher values degrade the signal into unif…

17:17
2026-09-27
huggingface.co
artificial-intelligence

Inference, semantics, questioning

A retired technologist seeking to work around RAG-driven inaccuracies was advised to experiment with query clarification, also called ambiguity-aware RAG, using DSPy to define a "clarify or answer" mo…

17:05
2026-09-27
huggingface.co
ai-agents

Cad/sldw mcp tool using

Meta's Muse Glimmer 30B, released August 2026 under Apache 2.0, scores 75.5 on the MCP-Atlas benchmark for MCP tool use, the highest of any model runnable on a single consumer GPU, versus 62.5 for Qwe…

14:24
2026-09-27
huggingface.co
large-language-models

LLMs perform worse than random at pro-active investigation

A paper titled "SherlockBench, Where Large Language Models Under-Perform Random Heuristics" (DOI 10.5281/zenodo.16253500) reports that large language models performed worse than random chance on pro-a…

12:39
2026-09-27
huggingface.co
ai-infrastructure

Error 429 while using HF Spaces

Hugging Face Spaces users are receiving HTTP 429 errors with the HTML page "We had to rate limit you" when one Space calls another Space's *.hf.space URL, according to a Hugging Face forum thread. For…

00:12
2026-09-27
huggingface.co
ai-infrastructure

Nvidia RTX 5060

Nvidia's RTX 5060 is usable for current PyTorch and image-generation stacks, but older packaged environments such as Fooocus's official portable still default to torch==2.1.0 and xformers==0.0.23, cau…

← prev page 23 / 71 next →