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.
A New Framework for Evaluating Voice Agents (EVA)
Open the source for the full engineering note.
Creating with Sora Safely
To address the novel safety challenges posed by a state-of-the-art video model as well as a new social creation platform, we’ve built Sora 2 and the Sora app with safety at the foundation. Our approach is anchored in concrete protections.
A Visual Guide to Attention Variants in Modern LLMs
From MHA and GQA to MLA, sparse attention, and hybrid architectures
Build a Domain-Specific Embedding Model in Under a Day
Open the source for the full engineering note.
How we monitor internal coding agents for misalignment
How OpenAI uses chain-of-thought monitoring to study misalignment in internal coding agents—analyzing real-world deployments to detect risks and strengthen AI safety safeguards.
OpenAI to acquire Astral
Accelerates Codex growth to power the next generation of Python developer tools
State of Open Source on Hugging Face: Spring 2026
Open the source for the full engineering note.
Measuring progress toward AGI: A cognitive framework
We’re introducing a framework to measure progress toward AGI, and launching a Kaggle hackathon to build the relevant evaluations.
Holotron-12B - High Throughput Computer Use Agent
Open the source for the full engineering note.
Introducing GPT-5.4 mini and nano
GPT-5.4 mini and nano are smaller, faster versions of GPT-5.4 optimized for coding, tool use, multimodal reasoning, and high-volume API and sub-agent workloads.
OpenAI Japan announces Japan Teen Safety Blueprint to put teen safety first
OpenAI Japan announces the Japan Teen Safety Blueprint, introducing stronger age protections, parental controls, and well-being safeguards for teens using generative AI.
Equipping workers with insights about compensation
New research shows Americans send nearly 3 million daily messages to ChatGPT asking about compensation and earnings, helping close the wage information gap.
Why Codex Security Doesn’t Include a SAST Report
A deep dive into why Codex Security doesn’t rely on traditional SAST, instead using AI-driven constraint reasoning and validation to find real vulnerabilities with fewer false positives.
Designing AI agents to resist prompt injection
How ChatGPT defends against prompt injection and social engineering by constraining risky actions and protecting sensitive data in agent workflows.
From model to agent: Equipping the Responses API with a computer environment
How OpenAI built an agent runtime using the Responses API, shell tool, and hosted containers to run secure, scalable agents with files, tools, and state.
Wayfair boosts catalog accuracy and support speed with OpenAI
Wayfair uses OpenAI models to improve ecommerce support and product catalog accuracy, automating ticket triage and enhancing millions of product attributes at scale.
Rakuten fixes issues twice as fast with Codex
Open the source for the full engineering note.
Improving instruction hierarchy in frontier LLMs
IH-Challenge trains models to prioritize trusted instructions, improving instruction hierarchy, safety steerability, and resistance to prompt injection attacks.
New ways to learn math and science in ChatGPT
ChatGPT introduces interactive visual explanations for math and science, helping students explore formulas, variables, and concepts in real time.
Introducing Storage Buckets on the Hugging Face Hub
Open the source for the full engineering note.
Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries
Open the source for the full engineering note.
From games to biology and beyond: 10 years of AlphaGo’s impact
Ten years since AlphaGo, we explore how it is catalyzing scientific discovery and paving a path to AGI.
OpenAI to acquire Promptfoo
OpenAI is acquiring Promptfoo, an AI security platform that helps enterprises identify and remediate vulnerabilities in AI systems during development.
Ulysses Sequence Parallelism: Training with Million-Token Contexts
Open the source for the full engineering note.
LeRobot v0.5.0: Scaling Every Dimension
Open the source for the full engineering note.