» Tag
ai
1051 postsA Sociotechnical Threat Model for AI-Driven Smart Home Devices
This study proposes a sociotechnical threat model addressing privacy risks faced by domestic workers using AI-driven smart home devices.
Building Multi-Tenant, Multi-Tier Memory for AI Agents
Explore memory management design for AI agents in multi-tenant systems.
Building Self-Improving AI Systems with Automated Feedback Loops
The importance of automated feedback loops for self-improving AI systems. Critical insights for developers.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comAgent OS: An Open-Source Harness Around Coding Models
Agent OS is an open-source, local-first AI framework that wraps coding models with memory, sandboxed execution, verification, and human-approved actions.
Nvidia Spectrum-X Ethernet Multiplane Network Architecture Unveiled
Nvidia unveiled the Spectrum-X Ethernet Multiplane Network at Hot Chips 2026, scaling AI factory networking by 64 times.
Sablejs 2.0 – An AOT Sandbox for AI-Generated JavaScript
Sablejs 2.0 offers an AOT sandbox for fast and debuggable execution of AI-generated JavaScript.
Nvidia's Groq 3 LPU Benchmarks: Insights and Implications
Nvidia's first benchmarks for Groq 3 LPU technology validate its $20 billion investment.
Integrating Security in the AI Agent Stack
Explore the critical layers and controls for securing AI agents based on NVIDIA's research.
Your AI Benchmark Might Be Measuring the Harness, Not the Model
Discover how software bugs can impact AI model evaluation. Understanding the role of the measurement system is crucial for assessing true model performance.
The End of Cheap Data: Rethinking the Scaling Laws
The shift from cheap passive data to interaction data is crucial for AI. Engineers must focus on creating high-quality environments for effective learning.