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 21 Aug.
Building Agents that Don't Break Themselves
Building agents is fun. Rebuilding agents that break themselves… less so. A lot of Fly people are building agents with less of a penchant for self-destruction by teaching their agents to do anything risky in a Sprite. You get an agent that stays alive long enough to actually use its snazzy self-impr...
Introducing the OpenAI Economic Research Exchange
OpenAI launches the Economic Research Exchange to study AI’s impact on jobs, productivity, and the economy. Applications are now open for selected research projects.
The Open Source Community is backing OpenEnv for Agentic RL
Open the source for the full engineering note.
Search and act across Datadog to resolve issues faster with Bits Chat
Bits Chat lets you search, visualize, and take action across Datadog using natural language, without losing context or switching tools.
Monitor Claude Enterprise activity with Datadog Cloud SIEM
Use the Datadog Claude Compliance API integration to monitor Claude Enterprise activity, detect risky behavior, and investigate events.
Why AI code optimization needs production-grounded benchmarks
Learn how Datadog’s DODO optimizer grounds AI-driven code optimization in live production telemetry, using CPU profiles and real call samples to generate accurate benchmarks and find meaningful speedups in mature services.
LLM Research Papers: The 2026 List (January to May)
A curated roundup of notable LLM research papers that came out this year
Give your AI agents live Datadog access from the command line
Learn how Pup CLI gives AI agents secure, token-efficient access to the full Datadog platform from the command line, with no long-lived API keys required.
Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI
Open the source for the full engineering note.
NVIDIA Nemotron 3 Ultra Powers Faster, More Efficient Reasoning for Long-Running Agents
Single-turn chatbots are evolving into long-running agents that can reason, maintain context, use tools, and run efficiently across many turns to complete...
How Endava is redesigning software delivery around AI agents
Learn how Endava is using AI agents, ChatGPT Enterprise, and Codex to accelerate software delivery, automate workflows, and build an AI-native culture across the enterprise.
Dreaming: Better memory for a more helpful ChatGPT
ChatGPT introduces a new memory system to better remember preferences, keeping context fresh and relevant across conversations.
Discord Patch Notes: June 4, 2026
Check out the finer details of the more technical fixes implemented into Discord recently.
Biodefense in the Intelligence Age
An action plan for AI-powered biological resilience
Designing the hf CLI as an agent-optimized way to work with the Hub
Open the source for the full engineering note.
New ways to turn global demand into revenue
At Sessions 2026, Stripe unveiled dozens of products and capabilities to help businesses turn global demand into revenue. See how to go global faster with localized checkout and Adaptive Pricing, smarter fraud tools, multicurrency treasury support, and automated tax compliance.
The future of agentic commerce is here
Explore how AI agents are transforming commerce at Stripe’s Agentic Commerce Next roadshow. Reserve your spot in Seattle.
Rethinking risk in the age of AI
Join senior risk and payments leaders in Seattle to explore how AI is reshaping fraud strategy. Seats are limited.
Introducing Bits Agent Builder: Build agentic workflows for alert response and remediation
Learn how you can build custom AI agents to automate complex operational tasks.
When failover isn’t safe: Building high-availability PostgreSQL on Kubernetes
During a reliability gameday, Datadog engineers discovered that their PostgreSQL clusters couldn’t safely fail over. Here’s how the team redesigned them for high availability using Patroni and synchronous replication.
Introducing new capabilities to GPT-Rosalind
GPT-Rosalind advances life sciences research with enhanced biological reasoning, medicinal chemistry expertise, genomics analysis, and experimental workflow capabilities.
Direct Preference Optimization Beyond Chatbots
Open the source for the full engineering note.
How Wasmer used Codex to build a Node.js runtime for the edge
See how Wasmer used Codex with GPT-5.5 to build a Node.js runtime for the edge, accelerating development 10x to 20x and shipping in weeks instead of months.
A blueprint for democratic governance of frontier AI
OpenAI outlines a blueprint for U.S. governance of frontier AI, proposing a federal framework for safety, resilience, and national security.
OpenAI public policy agenda
OpenAI outlines its public policy agenda for AI, including safety, youth protection, workforce transition, and global standards to ensure AI benefits society.