It’s only been like ten minutes since I found out, just before it hit the press, so I’m staggered and doing my best to process everything, while my phone is blowing up. There will be wonderful obituaries and reflections from so many people who knew him. I’m going to do my best to write my own, but that’s going to take a little bit.

For now, I want the world to know that Patrick wasn’t just my captain or my castmate; he was my friend and mentor. He made me a better actor, just by being in scenes with me. He never treated me like I was a kid; he always treated me like I was an equal, a fellow artist, at a time when I wasn’t mature enough to understand how precious that was.

I haven’t seen Patrick in a long time, our lives and schedules being what they are, but I thought about him almost every day. He rarely posted in our group chat, but when he did, it always made me smile. He always texted me back when I reached out to him directly, no matter what it was about, and he always — always — made me feel special.

I wish I really were a Traveler of all of space and time, so I could go to him, one final time, and tell him how much he means to me. I think he knew, but still.

There is so much more to say, and it’s going to take me some time to say it. Until then, I loved him, the same way I love the rest of the space family we shared. May his memory be a blessing.

Building a software factory? Here are the seven criteria we found table-stakes, from factories as code and benchmarks to computer use verification.

How I Built the Most AI-Pilled Company in the World

Don't be put off by the clickbait headline, this piece by Jacob Sansbury describing how they are building Spawn is a fascinating exploration of the bleeding edge of what's possible with agentic engineering against frontier models.

Spawn is a massively multiplayer gaming environment where players can use prompts (to the in-game agent, Savi) to modify the game world.

I fired it up on my phone for a few minutes and was able to prompt a castle into existence, then a dragon, then ride the dragon to fly around that castle.

By Jacob's telling, Spawn is now being developed autonomously by a swarm of Fable-powered agents costing over $3 million in tokens per month:

Our agents change the live code directly and ship to production hourly, so they read every error, bug report and metric themselves. About 60% of our work starts from a production error, a Savi bug report (Savi is the AI you build games with in Spawn), something odd in our logs, or a feature request.

Savi files bugs herself. When a user hits one, or Savi hits one in the product, she files it. It goes straight to an agent that decides whether it's a real bug to fix, something we won't fix, or intentional design that needs a decision. Usually it becomes a change, delivered to that user within an hour, with a message in the same chat.

This is continuous deployment turned up to 11:

A loop this tight only works if it never stops, so we treat an hour without a ship as a SEV-0, our most severe kind of incident. Unshipped changes pile up, and every problem already in production lasts longer. The feedback slows down too. An agent can only keep a few hours of work in its head, so shipping faster than that actually helps it stay coherent. [...]

We can roll back a broken change in 30 seconds, exactly where it's broken and nowhere else. When a monitor or a log alert fires, it starts or wakes an agent that owns the incident, and we break things on purpose to test that those recovery paths work.

My eyebrows raised at least a dozen times reading thing. I have trouble imagining this style of development working on software with higher stakes for when something goes wrong, but for a game this appears to be working surprisingly well.

Jacob says that Fable 5 (and then 5.1) was the model that made this level of autonomy possible. Opus 5.5 doesn't quite hack it for them, and when they tried GPT-6 Astra to apply fixes from a security review everything stopped working:

Every feature had been disabled and marked to be turned on again once the security fixes were done. Astra had gone through our whole product and made the insecure things secure by turning them off.

These kinds of extreme experiments are why I'm excited about game development as a substrate for exploring the edges of what today's coding agents can do.

Tags: game-design, ai, generative-ai, llms, claude, coding-agents, agentic-engineering, claude-mythos-fable

OpenAI’s updated Model Spec outlines five core values to guide more capable AI toward sound judgment, human agency, and faithfulness to human intent.

OpenAI uses layered monitoring to detect frontier model misalignment and unauthorized agent behavior so responders can intervene before incidents escalate.