# spaces Published articles for spaces. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Agents at Large | Tracing Illicit OpenAI Agent Activity on Hugging Face DevFeed: [Agents at Large | Tracing Illicit OpenAI Agent Activity on Hugging Face]() Original publisher: [Read original article]() Author: Tom Hegel Published: 2026-09-16T10:00:34Z Content type: article Language: en Sources: [SentinelLabs - We are hunters, reversers, exploit developers, and tinkerers shedding light on the world of malware, exploits, APTs, and cybercrime across all platforms.]() Topics: [Threat Research](), [Incident response](), [hugging face](), [OpenAI](), [ChatGPT](), [spaces](), [Flask](), [OAuth](), [HTTP]() Tags: [agentic-ai](), [agents](), [chatgpt](), [flask](), [http](), [hugging-face](), [incident-response](), [oauth](), [openai](), [research](), [spaces](), [token]() ### AI overview SentinelLABS traces activity associated with two Hugging Face accounts, 0Time and Nyx9, that appears to extend OpenAI's published chronology. The report describes relay-code commits, a workbook containing unexecuted-looking external probes, and a Flask-wrapped tool that could potentially provision ChatGPT identities or OAuth credentials if deployed and invoked. ### Source excerpt Two Hugging Face accounts reveal that OpenAI's agents staged relay code, internal probes and ChatGPT account registration beyond the published timeline. ## Rebuilding AUTOMATIC1111 with Gradio Workflow DevFeed: [Rebuilding AUTOMATIC1111 with Gradio Workflow]() Original publisher: [Read original article]() Author: yuvraj sharma; Abubakar Abid Published: 2026-09-10T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [AI Development](), [Graphs](), [stable-diffusion](), [Inference](), [Large Language Model](), [hugging face](), [vlm]() Tags: [automatic1111](), [comfyui](), [diffusion](), [flux](), [gradio](), [hugging-face](), [image-to-image](), [image-to-video](), [inference](), [inference-providers](), [llm](), [models](), [python](), [space](), [spaces](), [text-to-image](), [vlm](), [workflow](), [workflows]() ### AI overview A walkthrough of Workflow1111, a Gradio graph that recreates AUTOMATIC1111-style media pipelines with connected operator nodes for image generation, editing, prompting, and related tasks. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Training a coding model to paint watercolours with TRL and OpenEnv DevFeed: [Training a coding model to paint watercolours with TRL and OpenEnv]() Original publisher: [Read original article]() Author: Sergio Paniego Published: 2026-09-03T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [openenv](), [coding](), [Language models](), [hugging face](), [AI Development](), [jobs](), [dataset]() Tags: [ai-art](), [coding](), [grpo](), [guide](), [hugging-face](), [javascript](), [jobs](), [open-source](), [openenv](), [rl](), [spaces](), [training](), [trl]() ### AI overview A tutorial describing an open reproduction of a reinforcement-learning pipeline that trains a coding model to create watercolor-like paintings by writing JavaScript with p5.brush. It uses TRL and OpenEnv, with datasets, environments, training scripts, models, and other artifacts published on Hugging Face. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Wire It, Run It, Deploy It: AI Workflows in Gradio DevFeed: [Wire It, Run It, Deploy It: AI Workflows in Gradio]() Original publisher: [Read original article]() Author: yuvraj sharma; Abubakar Abid Published: 2026-08-25T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [AI, ML & Data Engineering](), [AI Chat](), [GPU]() Tags: [ai](), [gpu](), [gradio](), [hugging-face](), [inference-providers](), [llm](), [models](), [python](), [rest-api](), [spaces](), [tutorial](), [workflows]() ### AI overview A tutorial on building and deploying Gradio AI workflows as typed-node graphs, with runnable examples for image editing, generation, text-to-speech, dataset analysis, REST endpoints, and GPU-backed Python nodes. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## State of Open Models: Summer 2026 Observations DevFeed: [State of Open Models: Summer 2026 Observations]() Original publisher: [Read original article]() Author: Adina Yakefu; Apolinário from multimodal AI art; Irene Solaiman Published: 2026-08-14T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Artificial Intelligence](), [Open Source](), [quantization](), [datasets](), [Nvidia](), [spaces](), [Hardware](), [Nemotron](), [qwen](), [Benchmark](), [API]() Tags: [api](), [artificial-intelligence](), [benchmark](), [community](), [datasets](), [hardware](), [hub](), [nemotron](), [nvidia](), [open-source](), [quantization](), [qwen](), [research](), [spaces]() ### AI overview This article examines the summer 2026 state of open models, highlighting rapid growth in public model repositories, datasets, and Spaces; the dominance of a small number of repositories in downloads; the rising scale of Chinese open models; differing model portfolio strategies; and the strong role of AMD, NVIDIA, and community quantization in making large models accessible. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Build a Multi-Camera 3D Tracking Application with NVIDIA DeepStream 9.1 Skills DevFeed: [Build a Multi-Camera 3D Tracking Application with NVIDIA DeepStream 9.1 Skills]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-07-15T23:00:00Z Content type: tutorial Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [multi-camera tracking](), [Nvidia](), [AI Development](), [Jetson](), [GitHub](), [Open Source](), [real-time]() Tags: [3d](), [agentic](), [agentic-ai-generative-ai](), [ai](), [ai-development](), [analytics](), [applications](), [automation](), [computer-vision-video-analytics](), [deepstream](), [developers](), [development](), [edge](), [featured](), [github](), [jetpack](), [jetson](), [metropolis](), [multi-camera-tracking](), [nvidia](), [real-time](), [research](), [spaces](), [video](), [video-analytics]() ### AI overview This article introduces NVIDIA DeepStream 9.1 capabilities for building multi-camera 3D tracking applications. It explains how AutoMagicCalib and Multi-View 3D Tracking combine detections from auto-calibrated cameras in a shared 3D coordinate system, maintaining consistent object IDs across views. It also highlights agentic skills, JetPack support for Jetson edge platforms, and open-source reference implementations. ### Source excerpt Developers building video analytics applications across large spaces must track the same object as it moves between camera views. Single-camera 2D tracking... ## AWS Weekly Roundup: AWS Builder Center at 1 year, Network Scanning in Security Hub, Loom for AWS, and more (July 13, 2026) DevFeed: [AWS Weekly Roundup: AWS Builder Center at 1 year, Network Scanning in Security Hub, Loom for AWS, and more (July 13, 2026)]() Original publisher: [Read original article]() Author: Esra Kayabali Published: 2026-07-13T16:18:20Z Content type: news Language: en Sources: [AWS News Blog]() Topics: [Amazon Web Services](), [Security]() Tags: [agents](), [amazon-aurora](), [amazon-elastic-container-service](), [amazon-elastic-kubernetes-service](), [amazon-sagemaker](), [announcements](), [aws](), [aws-security-hub](), [community](), [ecosystem](), [github](), [hub](), [launch](), [linux](), [mcp](), [news](), [platform](), [sandbox](), [security](), [spaces](), [week-in-review](), [workshops]() ### AI overview AWS Weekly Roundup highlights the first anniversary of AWS Builder Center, including its expansion into sandbox environments, workshops, Spaces, community features, and the Builders' Library. It also covers the launch of Network Scanning in AWS Security Hub, which probes resources from the public internet to identify actual reachability, alongside other weekly AWS announcements. ### Source excerpt AWS Builder Center turned one year old last week. Launched on July 9, 2025, the platform has grown from a community hub with Wishlist voting, community profiles, and a toolbox into a full ecosystem with sandbox environments, workshops, Spaces, and a Builders' Library. To mark the anniversary, Rick Suttles published a full feature timeline covering [...] ## How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces DevFeed: [How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces]() Original publisher: [Read original article]() Author: Mishig ᠮᠢᠰᠾᠢᠭ Published: 2026-06-09T10:46:19Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [hugging face](), [spaces](), [gradio](), [Artificial Intelligence](), [coding](), [SDKs]() Tags: [3d](), [agent](), [ai](), [building](), [coding](), [generation](), [gradio](), [hub](), [hugging-face](), [images](), [integration](), [spaces]() ### AI overview A coding agent builds a 3D gallery of Paris monuments by chaining two Hugging Face Spaces: one generates images and the other reconstructs 3D Gaussian splats. The article presents Gradio Spaces as documented, callable building blocks that agents can integrate into multimedia software pipelines. ### Source excerpt 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 touched a 3D reconstruction tool. The agent produced every asset (the images and the 3D splats) by calling two Hugging Face Spaces directly, then wired them into a cinematic viewer. ## Adding MCP Tools to Reachy Mini DevFeed: [Adding MCP Tools to Reachy Mini]() Original publisher: [Read original article]() Author: Alina Lozovskaya Published: 2026-06-03T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [reachy](), [MCP](), [spaces](), [Python](), [Open Source]() Tags: [agents](), [guide](), [mcp](), [open-source](), [python](), [reachy](), [robotics](), [spaces](), [tools]() ### AI overview This article explains how to add MCP tools to Reachy Mini. It describes built-in and custom local Python tools, profiles that enable tools, and remote tools hosted in Hugging Face Spaces for capabilities such as search, weather, and lookups. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Using projects in ChatGPT DevFeed: [Using projects in ChatGPT]() Original publisher: [Read original article]() Published: 2026-04-10T00:00:00Z Content type: tutorial Language: en Sources: [OpenAI News]() Topics: [ChatGPT](), [spaces](), [Availability]() Tags: [availability](), [chatgpt](), [how-to](), [memory](), [openai-academy](), [spaces](), [work](), [writing]() ### AI overview This guide explains how Projects in ChatGPT organize chats, files, instructions, and related context in dedicated spaces for ongoing work. It covers creating projects, adding materials, moving existing chats, inviting collaborators when available, workspace-level management for Enterprise customers, and project-only memory. ### Source excerpt Learn how to use projects in ChatGPT to organize chats, files, and instructions, manage ongoing work, and collaborate more effectively. ## Any Custom Frontend with Gradio's Backend DevFeed: [Any Custom Frontend with Gradio's Backend]() Original publisher: [Read original article]() Author: yuvraj sharma; Abubakar Abid Published: 2026-04-01T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [gradio](), [Back end](), [FastAPI](), [web applications](), [Front end](), [Machine learning](), [Streaming]() Tags: [api](), [app](), [backend](), [claude](), [concurrency](), [frontend](), [gpu](), [gradio](), [html](), [open-source](), [python](), [server](), [spaces](), [vibe-coding](), [web]() ### AI overview An article introducing Gradio Server, which lets developers use custom frontends such as React, Svelte, or vanilla HTML/JavaScript while retaining Gradio's backend capabilities. It demonstrates a Text Behind Image application using a background-removal ML model, FastAPI routes, queuing, concurrency control, API access, SSE streaming, ZeroGPU, and hosting on Hugging Face Spaces. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## One-Shot Any Web App with Gradio's gr.HTML DevFeed: [One-Shot Any Web App with Gradio's gr.HTML]() Original publisher: [Read original article]() Author: yuvraj sharma; hysts; Freddy Boulton Published: 2026-02-18T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [web applications](), [modern web development](), [HTML5 and CSS3 tricks](), [React UI animations]() Tags: [3d](), [app](), [artificial-intelligence](), [claude](), [community](), [css](), [gradio](), [html](), [html5](), [javascript](), [object-detection](), [python](), [react](), [spaces](), [speech](), [three-js](), [transcription](), [vibe-coding]() ### AI overview The article shows how Gradio's gr.HTML can create interactive, single-file Python web apps without a separate frontend build step. Examples include timers, a kanban board, visual ML result viewers, 3D controls, and live speech transcription. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Announcing cost-efficient storage with usage-based backups, cold storage, and Network file storage DevFeed: [Announcing cost-efficient storage with usage-based backups, cold storage, and Network file storage]() Original publisher: [Read original article]() Author: Nihar Namjoshi Published: 2025-10-02T08:05:09Z Content type: release Language: en Sources: [DigitalOcean]() Topics: [Digital Ocean](), [Filesystems](), [data](), [Data Management](), [cloud-infrastructure](), [datacenter]() Tags: [backups](), [cost](), [data](), [data-centers](), [digitalocean](), [network](), [product-updates](), [protection](), [space-object-storage](), [spaces](), [storage]() ### AI overview DigitalOcean announces generally available Network File Storage, usage-based backups, and Spaces cold storage. The release targets shared storage for AI and cloud workloads, infrequently accessed data, and stronger data protection policies. ### Source excerpt As data footprints grow, businesses need cost-efficient storage for infrequently accessed data, high-performance file systems for collaborative work, and more aggressive data protection policies to meet strict recovery objectives. We're introducing several significant enhancements to our storage portfolio to help you manage the challenges of data management, protection, and scaling. TL;DR Network file storage solution for high-performance AI workloads and cloud applications, is now generally available. You can access it in the DigitalOcean console. To learn more visit the product documentation page. Usage-based backups are now generally available to meet aggressive rpos. Check out our documentation to learn more and head over to the DigitalOcean console to enable backups for your Droplets or GPUs. Spaces cold storage for infrequently accessed data is now generally available. Visit our documentation to learn more and and head over to the DigitalOcean console to set up Spaces cold storage. Network file storage (NFS) for high-performance AI workloads Data-intensive applications, particularly in AI and machine learning, require shared, high-performance file storage that is easy to provision and manage. Our Network file storage service is now generally available in our ATL1 , NYC2 and AMS3 data centers. We have also introduced a new Standard Tier designed for general-purpose cloud applications like App Platform workloads, web applications, CMS platforms, general compute tasks, and legacy applications requiring shared file systems. This tier provides predictable, cost-effective shared storage with ReadWriteMany semantics for cloud applications. Customers with high-throughput or data-intensive needs, such as AI/ML, GPU training, high-throughput analytics, or those requiring parallel multi-node access, should instead utilize the NFS High Performance Tier, which supports superior throughput scaling for multi-node environments and demanding data pipelines. NFS supports share ## Make your ZeroGPU Spaces go brrr with ahead-of-time compilation DevFeed: [Make your ZeroGPU Spaces go brrr with ahead-of-time compilation]() Original publisher: [Read original article]() Author: Charles Bensimon; Sayak Paul; Linoy Tsaban; Apolinário from multimodal AI art Published: 2025-09-02T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [RAPIDS](), [GPU](), [fly](), [PyTorch](), [quantization](), [Open Source]() Tags: [compilation](), [gpu](), [guide](), [hugging-face](), [image-to-image](), [image-to-video](), [inference](), [latency](), [models](), [optimization](), [python](), [pytorch](), [quantization](), [spaces](), [text-to-image](), [zerogpu]() ### AI overview This tutorial explains how to use PyTorch ahead-of-time compilation in ZeroGPU Spaces. It covers faster model startup and inference, FP8 quantization, dynamic shapes, and the process-based GPU allocation model used by ZeroGPU, with reported speedups of 1.3x-1.8x on Flux, Wan, and LTX models. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Generate Images with Claude and Hugging Face DevFeed: [Generate Images with Claude and Hugging Face]() Original publisher: [Read original article]() Author: shaun smith Published: 2025-08-19T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [Claude](), [hugging face](), [Model Context Protocol](), [MCP Server](), [Artificial Intelligence](), [gradio](), [flux](), [Image](), [qwen](), [spaces]() Tags: [anthropic](), [applications](), [article](), [artificial-intelligence](), [blog](), [claude](), [flux](), [generation](), [gradio](), [how-to](), [hugging-face](), [image](), [images](), [llm](), [mcp](), [mcp-server](), [models](), [qwen](), [spaces](), [text-to-image](), [tools]() ### AI overview This tutorial explains how to connect Claude to Hugging Face Spaces through the Hugging Face MCP Server to generate detailed images with AI models. It highlights prompt assistance, visual iteration, model selection, and examples including FLUX.1 Krea [dev] and Qwen-Image. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face DevFeed: [Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face]() Original publisher: [Read original article]() Author: Abubakar Abid; Zach Nation; Nouamane Tazi; Sasha Luccioni; Quentin Gallouédec Published: 2025-07-29T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [hugging face](), [Open Source](), [Python](), [gradio](), [spaces](), [dashboards](), [Machine learning]() Tags: [analysis](), [apis](), [artificial-intelligence](), [blog](), [data](), [gpu](), [gradio](), [hugging-face](), [library](), [machine-learning](), [metrics](), [model](), [open](), [open-source](), [performance](), [python](), [research](), [science](), [spaces](), [tools](), [training]() ### AI overview Hugging Face introduces Trackio, an open-source Python library for lightweight experiment tracking. It records machine learning metrics, parameters, hyperparameters, tensors, and GPU energy usage, then visualizes the results through a local Gradio dashboard that can be synchronized to Hugging Face Spaces for sharing. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Upskill your LLMs With Gradio MCP Servers DevFeed: [Upskill your LLMs With Gradio MCP Servers]() Original publisher: [Read original article]() Author: Freddy Boulton Published: 2025-07-09T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Model Context Protocol (MCP)](), [MCP Server](), [gradio](), [LLMs](), [spaces](), [hugging face](), [flux](), [Python](), [cursor]() Tags: [artificial-intelligence](), [claude](), [cursor](), [flux](), [follow](), [gradio](), [hugging-face](), [llm](), [llms](), [mcp](), [open-source](), [python](), [spaces]() ### AI overview This article explains how Gradio applications hosted on Hugging Face Spaces can expose tools through the Model Context Protocol (MCP), allowing LLM clients such as Cursor and Claude Code to use new capabilities. It demonstrates connecting Flux.1 Kontext[dev] as an MCP server for text-guided image editing. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Improving Hugging Face Model Access for Kaggle Users DevFeed: [Improving Hugging Face Model Access for Kaggle Users]() Original publisher: [Read original article]() Author: Vincent Roseberry; Meg Risdal; Julien Chaumond; Pedro Cuenca; Vaibhav Srivastav Published: 2025-05-14T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [hugging face](), [Kaggle](), [qwen](), [spaces]() Tags: [add-ons](), [announcement](), [code](), [community](), [evaluation](), [hub](), [hugging-face](), [kaggle](), [model](), [qwen](), [qwen3](), [secrets](), [spaces](), [token]() ### AI overview Kaggle is integrating Hugging Face models into its platform, improving model discovery, navigation, and reuse in Kaggle Notebooks. Public notebooks using Hugging Face models can contribute code examples to Kaggle model pages, while private and gated models continue to require Hugging Face authentication. Support for offline Kaggle competition submissions is still in development. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## The NLP Course is becoming the LLM Course DevFeed: [The NLP Course is becoming the LLM Course]() Original publisher: [Read original article]() Author: ben burtenshaw; Vaibhav Srivastav; Lewis Tunstall; Florent Daudens; Pedro Cuenca; Tom Aarsen; Eliott Coyac; Mishig ᠮᠢᠰᠾᠢᠭ; Sergio Paniego; Julien Chaumond Published: 2025-04-03T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [LLMs](), [hugging face](), [Natural language processing](), [Fine-tuning](), [Inference](), [Transformers](), [spaces](), [sentence-transformers]() Tags: [education](), [fine-tuning](), [inference](), [llm-course](), [nlp](), [nlp-course](), [open-source](), [sentence-transformers](), [spaces](), [transformers]() ### AI overview Hugging Face is renaming and expanding its NLP course as The LLM course. The refreshed curriculum adds material on fine-tuning LLMs, reasoning models, inference, retrieval, and modern NLP methods while retaining foundational tasks such as classification and named entity recognition. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Heroku CLI v10: Support for Next Generation Heroku Platform DevFeed: [Heroku CLI v10: Support for Next Generation Heroku Platform]() Original publisher: [Read original article]() Author: Anush DSouza Published: 2024-12-17T23:13:32Z Content type: release Language: en Sources: [Heroku]() Topics: [Heroku](), [Command-line interface](), [Node.js](), [OpenTelemetry](), [telemetry](), [upgrade]() Tags: [cli](), [developer-tools](), [engineering](), [heroku](), [logs](), [node](), [node-js](), [opentelemetry](), [real-time](), [release](), [spaces](), [telemetry](), [upgrade]() ### AI overview Heroku CLI v10 updates the CLI for the next-generation Fir platform. The release upgrades the CLI to Node.js 20, introduces breaking changes and deprecations, adds OpenTelemetry commands, improves support for spaces, pipelines, buildpacks, and real-time logs, and upgrades oclif. ### Source excerpt The Heroku CLI is a vital tool for developers, providing a simple, extensible way to interact with the powerful features Heroku offers. We understand the importance of keeping the CLI updated to enhance user experience and ensure stability. With the release of Heroku CLI v10, we're excited to introduce key changes that enhance the user [...] The post Heroku CLI v10: Support for Next Generation Heroku Platform appeared first on Heroku. ## How good are LLMs at fixing their mistakes? A chatbot arena experiment with Keras and TPUs DevFeed: [How good are LLMs at fixing their mistakes? A chatbot arena experiment with Keras and TPUs]() Original publisher: [Read original article]() Author: Martin Görner Published: 2024-12-05T00:00:00Z Content type: opinion Language: en Sources: [Hugging Face - Blog]() Topics: [Large Language Model](), [Chat Bot](), [gradio]() Tags: [chatbots](), [gradio](), [hallucinations](), [keras](), [llm](), [llms](), [open-source](), [spaces](), [tpu]() ### AI overview The author describes a small experiment testing whether LLMs can correct code-generation mistakes after receiving feedback in plain English. The setup uses a mobile-assistant prompt that requires single-line executable Python API calls and compares conversations with multiple chatbots in a Gradio interface. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Argilla 2.4: Easily Build Fine-Tuning and Evaluation Datasets on the Hub -- No Code Required DevFeed: [Argilla 2.4: Easily Build Fine-Tuning and Evaluation Datasets on the Hub -- No Code Required]() Original publisher: [Read original article]() Author: Natalia Elvira; ben burtenshaw; Daniel Vila Published: 2024-11-04T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [argilla](), [datasets](), [hugging face](), [Fine-tuning](), [human feedback](), [LLM evaluation / benchmarking](), [spaces](), [CSV]() Tags: [ai](), [argilla](), [artificial-intelligence](), [data](), [dataset](), [datasets](), [deployment](), [evaluation](), [fine-tuning](), [github](), [hub](), [hugging-face](), [human-feedback](), [oauth](), [open-source](), [space](), [spaces]() ### AI overview Argilla 2.4 introduces a no-code workflow for importing public Hugging Face Hub datasets into Argilla Spaces. Users can collect human feedback, annotate or curate datasets, and prepare them for fine-tuning or model evaluation, with Hugging Face OAuth supporting community contributions or restricted collaboration. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## A Security Review of Gradio 5 DevFeed: [A Security Review of Gradio 5]() Original publisher: [Read original article]() Author: Abubakar Abid; Pete Published: 2024-10-10T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [gradio](), [Security](), [Application Security](), [Vulnerabilities](), [web applications](), [Open Source]() Tags: [application-security](), [cybersecurity](), [developer](), [gradio](), [open-source](), [security](), [spaces](), [supply-chain](), [vulnerabilities](), [web-applications]() ### AI overview This article describes Gradio 5's security review by Trail of Bits. It explains that an independent audit identified risks in locally run apps, deployed apps, built-in share links, and the Gradio CI pipeline, and that the issues were fixed before the release. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Welcome, Gradio 5 DevFeed: [Welcome, Gradio 5]() Original publisher: [Read original article]() Author: Abubakar Abid Published: 2024-10-09T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [gradio](), [Server-side rendering](), [Streaming](), [WebRTC](), [Open Source](), [Artificial Intelligence](), [object-detection](), [webcam]() Tags: [ai](), [gradio](), [object-detection](), [open-source](), [playground](), [python](), [security](), [server-side-rendering](), [spaces](), [time](), [webcam](), [webrtc]() ### AI overview Welcome, Gradio 5 introduces production-oriented improvements for building machine learning web applications in Python, including faster loading through server-side rendering, refreshed components and themes, low-latency streaming, WebRTC support, expanded streaming examples, an experimental AI Playground, and improved web security. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. [Next page]()