Researchers released ArguLens, an open-source automated essay scoring system that decomposes scoring into three components: a discourse-move classifier, a LightGBM scorer, and a label-aware feedback g…
Hugging Face user AbstractPhil reports that their ZeroGPU Space 'AbstractPhil/alephllm-chat' builds successfully but never receives a hardware allocation, with the runtime API showing 'hardware.curren…
MiniMaxAI released MiniMax Music 3, an open text-to-music model that generates full songs with vocals, structured arrangements, and tracks up to five minutes long as 32 kHz, 16-bit stereo WAV. The mod…
MiniMax Music 3, an open music generation model from MiniMax, generates full structured songs up to five minutes long from text prompts and optional lyrics, but hands-on testing found solid English vo…
Hugging Face's OAuth `read-billing` scope only checks whether a user has a payment method set up, not access to bank account details, according to the company's documentation. Users concerned about au…
Gradio, a Hugging Face-owned framework, awarded $10,000 in OpenAI Codex prizes to three small-model apps in its Build Small hackathon, with Tiny Narrator winning $5,000 for an accessibility tool that …
A developer has published a guide for deploying a GFPGAN-powered face-restoration demo using Gradio on Ubuntu 22.04. The setup includes running the app as a systemd service and exposing it through Ngi…
An indie developer built Bob's Bar, a Collaborative Multi-Persona Sandbox (CMPS) that runs entirely locally via Ollama, allowing multiple AI personas to converse with each other and the user. The tool…
University of Illinois Urbana-Champaign researchers have released an open-source AI teaching assistant on HuggingFace that runs 11 separate models in parallel for text/image retrieval, generation, mod…
Hugging Face users who see a 'You have exceeded your Pro GPU quota' error despite having loaded credits are likely misunderstanding the platform's separate billing systems, according to Hugging Face d…
AMD introduced an agentic RAG system called Enterprise Research Analyst that uses hipVS GPU-accelerated vector search as its retrieval backbone, demonstrating a multi-step pipeline that decomposes com…
An independent open-source developer has filed an official community complaint against Hugging Face, demanding the reversion of recent free-tier changes that eliminated CPU Basic instances, restricted…
A user deploying an app to Hugging Face Spaces encounters a NetworkError when attempting to fetch a resource after inputting a Hugging Face token. The app, built with AI assistance using a Gradio-base…
An anonymous developer recounts the four-year history of the AUTOMATIC1111 Stable Diffusion WebUI, from its creation in August 2022 to its decline by 2026. The project, which began as a single Gradio …
Hugging Face appears to have restricted free accounts from creating CPU Basic Gradio Spaces, leaving only ZeroGPU as the available runtime. Users report that Docker is marked as paid and switching to …
Hugging Face has restricted free-tier accounts from selecting Gradio as an SDK when creating a new Space, impacting a nonprofit that uses the platform for teaching AI/ML to teens. The organization is …
Hugging Face has restricted Gradio Spaces to paid plans, preventing new free-tier users from selecting Gradio as an SDK. The change disrupts a nonprofit's free AI/ML education program for teens, which…
A developer built DeployCraft AI, a tool that designs MLOps infrastructure by generating deterministic deployment blueprints from high-level inputs. The system uses a rules engine and Jinja2 templates…
A website owner reports that their Gradio-powered AI chatbot widget stopped working due to a CORS policy change in Gradio, which now requires the 'Access-Control-Allow-Credentials' header to be 'true'…
A developer built a fully working conversational AI agent on Databricks without custom tables or Vector Search, using only the built-in samples.tpch dataset. The stack includes OpenAI Agents SDK, Data…