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.
smolmachines / smolvm as a sandbox for untrusted Python & JavaScript
Research: smolmachines / smolvm as a sandbox for untrusted Python & JavaScript I tasked Claude Fable 5 running in Claude Code for web with the following research task: Put https://smolmachines.com through its paces as a fast secure sandbox. Explore what it would take to use this to run untrusted Pyt...
Quoting Jeremy Morrell
My hypothesis is that there is a new opportunity for Extensible Software on the web . LLMs radically lower the cost of authoring extensions, and modern sandbox primitives lower the deployment cost and provide good security boundaries. We can build our app as a solid, accountable core, and allow user...
Conceptual integrity and counting lines of code
Last week I recorded an episode of the Talking Postgres podcast with Claire Giordano on the subject of "How AI is changing software development". We had a really great conversation. Here are a couple of my highlights from a lightly edited transcript (prompt to Claude: "very minor edits to remove dis...
Developing NVIDIA Holoscan Applications with CLI, Skills, and AI Coding Agents
NVIDIA Holoscan is a platform for building real-time AI applications at the edge, from medical imaging to robotics. HoloHub is its companion repository: a...
Offering Zero Data Retention for frontier models
OpenAI reaffirms Zero Data Retention for eligible API customers and previews Private Safety Processing for advanced AI safety without compromising data privacy.
Building Federated Multimodal AI Workflows with NVIDIA FLARE
Modern vision-language models (VLMs) can support tasks such as visual question answering, captioning, and image-text reasoning. In practice, however, the data...
Post-Train NVIDIA Cosmos 3 Edge for On-Device Robot Control
Robots need policies that can adapt to their sensors, environments, and tasks while running on onboard computing hardware. World models offer a foundation for...
Evaluating AI Agent Skill Performance with NVIDIA SkillEvaluator
AI agents are only as effective as the context they receive. Even with capable models and well-documented NVIDIA libraries, agents can spend extra steps finding...
LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation
Open the source for the full engineering note.
Replit expands access to software creation with GPT-5.6 Luna
Replit introduces Free Mode, powered by GPT-5.6 Luna, so anyone can turn ideas into working software without worrying about token costs.
ChatGPT Ads expands across Europe
ChatGPT Ads is expanding to 31 European markets. Learn how advertisers can reach people as they explore, compare options, and make decisions.
Mojo🔥 is now open source
Mojo🔥 is now open source The Mojo programming language has been promising an open source release since May 2023 . Last week they shipped their 1.0 and today they have followed through on that original promise, releasing the compiler and toolchain under an Apache 2 license. When Mojo first launched ...
Strengthening democratic oversight in national security
OpenAI launches an initiative to strengthen democratic oversight of AI in national security, supporting government institutions with tools, training, and expertise.
How Much Memory Does Your Agent Actually Need?
Open the source for the full engineering note.
How AI Coding Agents Can Unlock Materials Simulation with NVIDIA ALCHEMI Toolkit
Atomistic simulation requires three things: knowledge of the science, compute-efficient implementation of simulations, and accessible interfaces to the...
Run Massive-Scale UMAP in Minutes Using Multiple GPUs—Without Losing Accuracy
Uniform Manifold Approximation and Projection (UMAP) is a dimensionality reduction technique widely used for visualization and feature extraction. Applications...
Partnering with CodeAI to prepare the first AI generation
OpenAI and CodeAI are partnering to help students build AI literacy, think critically about AI, and develop the skills to use and shape it responsibly.
Introducing ChatGPT for Teens: Built for learning, backed by protections
ChatGPT for Teens helps teens learn, think critically, and use AI with confidence, with stronger built-in protections, healthy-use features, and additional controls for parents.
Pacing model development in an era of cyber-critical capabilities
OpenAI is strengthening monitoring, alignment, and security for frontier AI models. See how new safeguards are guiding the pace of model development.
Asana cleared 5 years of engineering work in 2 weeks with Codex
Asana used OpenAI Codex to replace an outdated testing system in two weeks, completing work expected to take five years for about $12K.
How NVIDIA scales expertise with ChatGPT Work
NVIDIA teams use ChatGPT Work to reduce manual tasks, connect fast-moving signals, and scale successful workflows globally.
Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
Open the source for the full engineering note.
Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index
Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index That's the same score as GPT-5.6 Luna (max), and just one point behind GLM-5.2 (max) and DeepSeek V4 Pro 0813 (max) - that GLM is 753B and that DeepSeek is 1.7T parameters , and Luna is size unknown but presumably a whole lot bigge...
Same Cluster, 33 Points More Utilization: What Changed Was the Order
Open the source for the full engineering note.
Developing Nemotron 3.5 Lightning NVFP4 with QAD Using NVIDIA Model Optimizer
Teams customize their models to hit their targets for latency, speed, memory, and compute. With the open NVIDIA Nemotron family of models, developers can find...