AI Engineering
Practical ideas and tools for building with AI.
About this list
This reading list brings together items from the sources selected for AI Engineering. Open each item at its original source for the complete article, episode or video. This is a selection of current coverage, not a complete archive.
Latest podcasts
Newest first
What are you still paying for that you meant to cancel? I handed mine to an AI assistant: $1,285 a year cancelled so far. The prompt guide for the tedious part of yours
I’ll bet you’re still paying for something because canceling it has never made it to the top of your day. Getting into the account, figuring out the rules, and dealing with whatever happens next keeps losing to work, dinner, or a child who needs something.
OpenShell Moves Agent Safety Below the Model
NVIDIA’s Open Agent Safety Platform is worth reading as an infrastructure claim, not as a new prompt rule [NVIDIA
Claude Code’s Next Era — Thariq Shihipar, Anthropic
Shipping Opus/Sonnet 5.5, Mods, Plugins, Projects, Tag while Pacing the Frontier
Executive Briefing: You Bought Better Tools and Your Finished Work Still Waits
AI is making some people dramatically more productive. Getting that speed through the rest of the organization is a separate problem, and it isn’t solved by making the fast people teach everyone else.
When Tools Get in the Way Cuts Accuracy
The paper *When Tools Get in the Way* isolates a failure mode that is easy to miss in agent design: a model can answer worse when an unnecessary but
ToolGrad Turns Tool Failures Into Data
Google’s ToolGrad reframes tool-use training data as an execution problem before it is a prompt-writing problem. Instead of asking a model to invent a
OpenRouter: from Seed to Stripe — with OpenRouter’s Alex Atallah & AMP’s Anjney Midha
In 2023 most people doubted that there could be more than 1 or 2 frontier model labs. Now there are dozens.... and Stripe just bought the best known one for $7B.
OSWorld-Pro Exposes Click Failures
OSWorld-Pro turns desktop automation into a step-by-step audit. The paper extends OSWorld-style computer-use evaluation with process checks, so a model
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
GWM Worlds 2 uses persistent context and timed actions to steer a world model generating video and audio in real time.
Inside NVIDIA: What a world model actually is, and how it connects to the LLM you already use
NVIDIA builds tools for developers. That is the place to start if you want to understand why a company most people associate with chips is building models that can help simulate a factory, predict what happens when a robot moves, or generate actions for a machine. I went to NVIDIA last week to talk with Ming-Yu Liu, the vice president of Cosmos Lab. Cosmos is NVIDIA’s world-model effort. Early in our conversation, Ming-Yu explained the relationship between NVIDIA’s computers and everything the company builds around them.
Progress Hints Cut Tool-Call Waits
Tool-calling systems already know more about long-running work than the model server can see. A new paper, *Ask the Tool, Don’t Guess*, argues that the
Gemini 3.8 TTS Playground
Tool: Gemini 3.8 TTS Playground Google released two new Gemini text-to-speech models today - gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts. They come with a library of over 2,000 voices, plus the ability to create a custom voice with "just a 30-second audio sample of your voice or a voice you have the rights to use". I vibe coded this bring-your-own-key playground interface with GPT-6 Astra, taking advantage of the open CORS policy of the underlying Gemini API.
Design Engineering with Maggie Appleton
Maggie Appleton on what engineers can learn from designers, working with AI agents, and why human judgment still matters.
🔬Bio-security is an AI Arms Race - Eric Nguyen (CEO, Radical Numerics)
Radical Numerics is using biological chain-of-thought and multimodal perception to keep up with the bio-defense arms race, design new genomes and gain insights into biology itself.
BenchAgent Tests Multi-Agent Lift
BenchAgent gives multi-agent workflow design a useful test: hold the benchmark loader, tool access, answer contract, usage accounting and trajectory
🔬 An Oscar, Two Asteroids, and the Algorithm in Your sklearn: John Platt on AI for Science
We talked to Google’s Oscar winning “Giganerd” about automating science, solving climate change, and how future generations can contribute to science in the age of superintelligent AI
Your agent is giving you reasonable answers from half your context. A conversation with OpenAI
How do you turn individual AI ability into a team that learns faster, makes better decisions, and gives people some of their lives back? Last week, I went to OpenAI to ask.
Can Next-Turn Metrics Test Workflows?
The paper *When Better Turns Do Not Make Better Agents* tests a quiet failure in agent evaluation: a model can improve at predicting the next local action
Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI
The definitive Jev podcast with its lead creator.
Showing 20 of 48 podcasts
Know a source we’re missing? Tell us about it