Product engineering, system boundaries, and the tools I ship with.
20
Recent writing tagged Models.
Apple's 2026 model APIs made local, private-cloud, and third-party inference choices part of one native architecture instead of separate product bets.
Google's Gemini 3.5 launch paired a new model with managed execution, showing how much of an agent product now lives outside the model itself.
GPT-5.5 made long-running agent work the headline. The harder question is how to evaluate whether an agent can finish responsibly.
By subscribing you consent to email updates. You can unsubscribe anytime. See our Privacy Policy.
Follow me on X