Staff

Auto Added by WPeMatico

Pixel-Native RAG: A Practical Guide to Visual Document Indexing

ai, AI (Artificial Intelligence), Artificial Intelligence, Editors Pick, Language Model, Large Language Model, model context protocol, Staff, Technology, Tutorials

In this tutorial, we build a complete pixel-native retrieval-augmented generation pipeline from scratch and examine how document retrieval works without relying on conventional HTML parsing, text extraction, or fixed chunking strategies. We render web pages and PDF documents as images, divide them into overlapping tiles, generate multimodal embeddings with SigLIP, CLIP, or an optional Qwen3-VL […]

Pixel-Native RAG: A Practical Guide to Visual Document Indexing Read More »

Cursor Open-Sources Mixture-of-Kittens (MoK): A Deterministic MoE Training Megakernel for GB300 NVL72 Racks

agentic ai, ai, AI (Artificial Intelligence), AI Infrastructure, AI Shorts, Artificial Intelligence, Editors Pick, Large Language Model, Machine Learning, New Releases, Open Source, Software engineering, Staff, Tech News, Technology

Cursor Research has open-sourced Mixture-of-Kittens (MoK), the mixture-of-experts training megakernel behind its Composer models. MoK fuses every MoE communication and computation step into a single deterministic kernel. Cursor team reports up to 2.37x higher throughput than the strongest public baseline. It already powers Composer training across tens of thousands of GPUs. Is it deployable Yes,

Cursor Open-Sources Mixture-of-Kittens (MoK): A Deterministic MoE Training Megakernel for GB300 NVL72 Racks Read More »

Reflex Open Sources XY: A Rust-Backed Super-Fast Python Charting Library That Keeps 100 Million Point Charts Interactive

agentic ai, ai, AI (Artificial Intelligence), Applications, Artificial Intelligence, deep learning, Editors Pick, Machine Learning, New Releases, Open Source, Software engineering, Staff, Tech News, Technology

Reflex AI has released XY, an Apache-2.0 Python charting library for interactive 2D visualization. Most Python charting stacks create one drawable object per row, so past a few hundred thousand points, render, hover, and zoom degrade. XY moves the work into a native Rust core, sends the browser typed binary buffers instead of JSON, and

Reflex Open Sources XY: A Rust-Backed Super-Fast Python Charting Library That Keeps 100 Million Point Charts Interactive Read More »

Reflex Open Sources XY: A Rust-Backed Super-Fast Python Charting Library That Keeps 100 Million Point Charts Interactive

agentic ai, ai, AI (Artificial Intelligence), Applications, Artificial Intelligence, deep learning, Editors Pick, Machine Learning, New Releases, Open Source, Software engineering, Staff, Tech News, Technology

Reflex AI has released XY, an Apache-2.0 Python charting library for interactive 2D visualization. Most Python charting stacks create one drawable object per row, so past a few hundred thousand points, render, hover, and zoom degrade. XY moves the work into a native Rust core, sends the browser typed binary buffers instead of JSON, and

Reflex Open Sources XY: A Rust-Backed Super-Fast Python Charting Library That Keeps 100 Million Point Charts Interactive Read More »

Building an Advanced AI Skill Security Auditing Pipeline with NVIDIA SkillSpector, LangGraph, YARA Rules, SARIF, and CI Policy Gates

agentic ai, ai, AI (Artificial Intelligence), AI Agents, Applications, Artificial Intelligence, Editors Pick, Language Model, New Releases, Software engineering, Staff, Technology, Tutorials

In this tutorial, we build a workflow for evaluating the security posture of AI skills with NVIDIA SkillSpector. We create a synthetic skill marketplace containing clean, risky, malicious, and MCP-based examples, then scan each skill through SkillSpector’s LangGraph inspection pipeline. We examine risk scores, categorized findings, confidence levels, analyzer completeness, and executable-script indicators before organizing

Building an Advanced AI Skill Security Auditing Pipeline with NVIDIA SkillSpector, LangGraph, YARA Rules, SARIF, and CI Policy Gates Read More »

Y Combinator Open-Sources QM: An MIT-Licensed Multiplayer Agent Harness That Runs In Slack And The Web

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Infrastructure, AI Shorts, Applications, Artificial Intelligence, Editors Pick, Language Model, Large Language Model, Machine Learning, New Releases, Open Source, Software engineering, Staff, Tech News, Technology

Y Combinator team has open-sourced QM (quartermaster), the multi-agent harness it uses internally. QM is described as a multiplayer agent harness for work, running in Slack and on the web. YC team runs QM across accounting, legal, events, and engineering, including building QM itself. The whole project ships under the MIT license. YC frames the

Y Combinator Open-Sources QM: An MIT-Licensed Multiplayer Agent Harness That Runs In Slack And The Web Read More »

Genspark Open Sources GenOffice: A Free, Ad-Free AI Office Suite for macOS and Windows with Docs, Sheets, Slides, PDF

agentic ai, ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Editors Pick, Language Model, Machine Learning, New Releases, Open Source, Python, Staff, Tech News, Technology

Genspark has released GenOffice as open source under the Apache License 2.0. The repository describes it as an AI-native office suite for macOS and Windows: a word processor, a spreadsheet, a presentation editor and a PDF tool. The implementation is five Electron apps sharing one engine layer, built around AI editing as a first-class workflow

Genspark Open Sources GenOffice: A Free, Ad-Free AI Office Suite for macOS and Windows with Docs, Sheets, Slides, PDF Read More »

Evaluating Multimodal Vision Models with Moonshot PerceptionBench Using Robust Data Loading and Automated Judging

agentic ai, ai, AI (Artificial Intelligence), AI Infrastructure, Applications, Artificial Intelligence, Editors Pick, Language Model, Large Language Model, Staff, Technology, Tutorials

In this tutorial, we design an end-to-end evaluation workflow for PerceptionBench. This multimodal benchmark measures fine-grained visual perception capabilities across tasks such as OCR, counting, localization, contextual reasoning, comparison, depth understanding, and hallucination detection. We begin by configuring a Colab-compatible environment, installing the required libraries, and loading a balanced subset of the dataset through a

Evaluating Multimodal Vision Models with Moonshot PerceptionBench Using Robust Data Loading and Automated Judging Read More »

How to Secure AI Agents, MCP Servers, and LLM Apps in Production

agentic ai, ai, AI (Artificial Intelligence), AI Infrastructure, AI Shorts, Applications, Artificial Intelligence, deep learning, Editors Pick, Language Model, Large Language Model, Machine Learning, New Releases, Promote, Security, Software engineering, sponsored, Staff, Tech News, Technology, Uncategorized

Agents, MCP integrations, and LLM-powered applications are entering codebases faster than most security programs can track them. Mend.io’s new practitioner guide, ‘Securing AI agents, MCP servers & LLM apps: A practical framework’, targets that gap. It is organized around three moves: see what matters, fix what matters faster, protect AI in production and ships seven

How to Secure AI Agents, MCP Servers, and LLM Apps in Production Read More »

Alibaba Qwen Releases Qwen3.8-Max: A 2.4 Trillion Parameter MoE Model and the Most Capable One in the Qwen Family to Date

agentic ai, ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Editors Pick, Language Model, Large Language Model, Machine Learning, New Releases, Staff, Tech News, Technology, Vision Language Model

Alibaba’s Qwen team has made Qwen3.8-Max broadly available and confirmed that its open weights ship next week. A second checkpoint, Qwen3.8-27B, is also going open-weights. Qwen3.8-Max is a 2.4-trillion-parameter mixture-of-experts model. It accepts text, image and video as input and returns text. Is it deployable Yes, but the deployable surface depends on which artifact you

Alibaba Qwen Releases Qwen3.8-Max: A 2.4 Trillion Parameter MoE Model and the Most Capable One in the Qwen Family to Date Read More »