Very informative article. I was hazy on where NVLink sat in the local inference stack. This makes it very clear: to adapt consumer hardware that lacks multiple full x16 PCIe lanes.
I switched to Codex in November 2025 because I couldn't stand the smarmy, "You're absolutely right" anymore. Codex at the time offered less sycophancy and more pushback when I was actually wrong. I also feel it writes cleaner code since it follows my instructions better to not write unrequested code, not create unnecessary abstractions, and not reinvent any wheels.
I use LLMs on a tight-leash in HITL for web development, monitoring traces as it goes. I rarely use it for more than just writing code that I specify and I rarely let it "have it's head" and work unmonitored.
I use it on the API plan since I need it to be reliable. No outage issues that I can recall.
I used this a decade ago, and it was a joy to use for someone who grew up with Macromedia/Adobe Flash scripting.
In 2026, I would have thought that regular HTML/CSS would have caught up with this. Maybe it has, I don't do any animations anymore.
More or less our approach here too. They offered to help with our work at a loss for themselves, why not take them up on it? Not necessarily to hurt the AI labs, but just because we'd be foolish not to take something offered at such a discount.
Makes sense if they are planning to concede in Ukraine. The Russian economy is dependent on continued military buildup, so they will try to continue with that but go back to their cold war-era posturing with the forces and matériel produced.
Does this mean that work created with it can be copyrighted? Since the courts ruled that the inclusion of pilfered IP was the reason other model's work cannot be copyrighted, I would think so!
In that case, this is a completely different beast. It can maybe be used for things that need a durable copyright.