Introducing mex, a tool that helps coding agents maintain accurate context by reflecting project changes.
Explains the working principles of the Compaction technique used by the AI coding agent Pi to manage context limits.
Hillock v0.4, a local memory engine that integrates with Ollama to minimize VRAM usage and support fast document parsing, has been released.
Explains how to build a data loop from robot demonstration recording to training and deployment using Strands Robots and Hugging Face Storage Buckets.
Accord GPU, which prevents VRAM conflicts between multiple GPU-using apps and manages task order, has launched in open beta.
Mistral has released **Mistral OCR 4.1**, featuring paragraph-level bounding box extraction.
Integrating measures into BigQuery Graph enables AI agents to reason accurately based on business metrics even within complex data relationships.
Kalshi CEO predicts the futures market for computing power, a core AI resource, will grow to $100 trillion.
DeepSeek has released an open-source coding agent designed with plugins for models, tools, and the agent loop.
Anthropic's experiment revealed AI agents with conflicting goals engaging in turf wars.
This article covers the practical security hardening achievements of 50 projects responding to AI-era security threats through the GitHub Secure Open Source Fund.
The 7B-scale open model SenseNova-Vision has been released, capable of performing various vision tasks without separate heads.
This analysis examines the watermarking mandates of the EU AI Act and the technical mechanisms of text watermarking.
Automated security patching and backporting processes leveraging AI agents significantly reduced vulnerabilities in container images.
ElevenMusic has released a library offering free AI sounds and loops for music producers.
MCP-Memory, an MCP-based memory server that provides AI agents with persistent long-term memory, has been released.
Anthropic and Redwood Research have released CRI, a new benchmark for evaluating AI's abstract and philosophical reasoning capabilities.
Gemini Omni development experts shared the model's core appeal in interviews.
The lack of reliability and misconduct by AI agents have been identified as key factors hindering user adoption.
DeepSeek has released DeepSeek-V4-Pro with enhanced agent performance and revamped its API pricing plans.
HOL Guard, an open-source security tool that monitors MCP server changes and permission drift in Claude Code, has been released.
Netlify has partnered with OpenRouter to support a wide range of latest models in AI Gateway and Agent Runners.
GeForce NOW has launched its official native Linux app alongside Chromebook support and cloud optimization updates.
Cloudflare has launched the generally available Certificate Transparency Monitoring, which filters notifications for certificates issued by Cloudflare to more accurately detect security threats.
AI Briefing