Field Signal · Curated Reading
The Engineering
Signal.
High-signal field notes, architecture teardowns, and engineering writing from 50 publications. A focused reading queue for becoming a stronger end-to-end engineer. Updated 20 Aug.
How to Evaluate General-Purpose Robot Policies for Real-World Deployment
Robotics foundation models have made remarkable progress. Today's best systems can follow natural language instructions to pick, place, sort, and manipulate a...
Reducing High-Bandwidth Memory Bottlenecks in JAX-Based LLM Training with Host Offloading
Large language model (LLM) training workloads increasingly run into GPU memory limits before compute is fully used. Model weights, gradients, optimizer states,...
Kernel Fusion in NVIDIA CUDA: Optimizing Memory Traffic and Launch Overhead
There are many ways to optimize code for GPUs. In this post, you’ll learn how kernel fusion can improve memory bandwidth and reduce kernel launch overhead,...
AI Model Co-Design: Hardware-Friendly LLM Design
AI performance comes down to three dimensions: Accuracy: How well the model reasons and produces outputs Throughput: How many tokens per second a...
Accelerating End-to-End Co-Folding Performance with NVIDIA BioNeMo Agent Toolkit
Biomolecular structure prediction and co-folding with models like OpenFold3 are now mainstream, large-scale workloads powering drug discovery and protein...
Making agentic token costs visible in production
Learn where agentic token costs come from, how to reduce them across tool definitions, session history, and retrieval loops, and how to monitor spend.
Synthetic Data Generation for Financial AI Research with NVIDIA NeMo
Fine-tuning LLMs for financial natural language processing (NLP) is constrained by limited, imbalanced data. Real-world financial news overrepresents earnings...
A Practical Guide to GPU-Initiated Communication for Molecular Dynamics at Scale
Molecular dynamics (MD) simulations are among the most demanding workloads in computational science. Using them, researchers can observe atomic behavior in...
Untitled
The Agentic Data Plane is the governance and runtime layer that connects your AI agents to everything they act on. Learn what it does, why existing tools can't replace it, and what to look for in an enterprise-grade one.
Create a LangChain Deep Agents Harness Profile for NVIDIA Nemotron 3 Ultra to Improve Performance
Agentic systems often face a trade-off between accuracy and cost. The highest-performing proprietary frontier models and harnesses provide top accuracy but are...
Running Low-Latency Analytical Workloads with GPU-Accelerated Presto on NVIDIA GB200 NVL72
Presto is an open source, distributed SQL engine for running fast, interactive queries on very large datasets. On NVIDIA GPUs, Presto delivers peak performance...
ScyllaDB Is Now Supported in MCP Toolbox for Databases
Connect your AI agents to ScyllaDB using the new ScyllaDB integration in MCP Toolbox for Databases
Protect AWS Strands Agents with Datadog AI Guard
Monitor and help protect AWS Strands Agents by using Datadog AI Guard to evaluate prompts, model responses, and tool calls inline.
Monitor your .NET MAUI apps with Datadog RUM
Use the Datadog .NET MAUI SDK to monitor crashes, errors, ANR events, network performance, and user sessions across iOS and Android apps.
NVIDIA Vera CPU Boosts AI Factory Throughput to Accelerate Agentic Workloads
Agentic systems turn model reasoning into action through multi-step workflows that combine inference, tool use, code execution, retrieval, orchestration, and...
Develop Humanoid Robot Policies End-to-End with NVIDIA Isaac GR00T
As more teams move from humanoid robot bring-up to task-specific skill development, the need for repeatable development workflows is growing. Building humanoids...
Maximize Spectral Efficiency with AI-Native RAN and NVIDIA AI Aerial
Spectrum is one of the most valuable assets in wireless communications. Over the last 30 years, telecom operators in the US have spent more than $240B to...
Building an Analysis AI Agent for Industrial Alarm Management with NVIDIA Nemotron
Industrial machinery generates more alarms than technicians can triage. For each important alarm requiring follow-up, the technician pulls historical context,...
Agent Memory at Monster Scale with Mem0 and ScyllaDB Cloud
Combine Mem0’s memory management with ScyllaDB’s persistence features to deploy large-scale AI agents
Discord Patch Notes: July 7, 2026
Check out the finer details of the more technical fixes implemented into Discord recently.
Stream Oracle changes to ClickHouse in real time
A hands-on walkthrough of the new Oracle input in Redpanda Connect. No Debezium, no Kafka Connect runtime, no JVM.
DASH 2026 recap: Product news, sessions, and highlights
Catch up on the Datadog product and feature announcements, technical sessions, customer stories, and community activities from DASH 2026.
Enhancing Goodput in Large-Scale LLM Training with Nonuniform Tensor Parallelism
Training LLMs at massive scale brings unique infrastructure challenges, especially as jobs span thousands of GPUs and run for extended periods. The longer these...
ScyllaDB vs Aerospike, Wide-Column vs. Key/Value
Wide-column flexibility doesn’t have to come at the expense of performance -- see where the two models differ, where each one wins, and why you no longer have to choose
Monitor watchOS and visionOS apps with Datadog RUM
Monitor crashes, errors, and user sessions on watchOS and visionOS by using Datadog RUM with fully deobfuscated stack traces and no separate SDK required.