First things first: Happy Canada Day, everyone! Bonne fête du Canada, tout le monde !

Yes, I know. Starting a post that celebrates Canada Day with a giant title thanking China might feel a bit ironic, if not entirely contradictory. But stick with me for a minute. Because if you are a Canadian working in tech right now, navigating a world where our longest-standing friendship and alliance has ruptured into open hostility from the US government, you should be thanking them too.

For decades, the Canadian tech ecosystem operated under an unspoken assumption: we were fundamentally part of the same digital backyard as Silicon Valley. We relied on the same infrastructure, trusted the same partners, and assumed that a shared border meant shared access to the future of technology.

The rise of large language model regulation in the US has shattered that illusion. As LLMs became the foundational infrastructure for the next generation of software, the narrative shifted toward a suffocating, centralized reality. Suddenly, it looked like access to “intelligence” would be controlled by a couple of trillion-dollar American tech giants, operating under the tight regulatory grip and arbitrary “national security mandates” of an increasingly authoritarian and hostile US government. That’s… not great.

The message to us and to the rest of the world was clear: if you want to build next-gen software, you have to rent it from them and you have to behave or they’ll turn off the tap.

When the US government forced Anthropic to turn Fable and Mythos off a couple of weeks ago, it hit me how all of a sudden things could turn. And that’s when I starting thinking about how different things could have been had China not chosen the path of opensource.

The Open-Source Weapon

Had Chinese AI labs followed the American playbook, the trap would have snapped shut.

When the US president put measures to prevent chips from being sold to China, they inadvertently scored one of the biggest own goals ever, because faced with severe hardware restrictions and intense domestic competition, Chinese companies and research labs like Alibaba, Z.AI and Moonshot took a radically different path. While American companies felt safe in closing their gates, shifting from open research to aggressive, closed-source monopolies, the Chinese chose to weaponize open weights.

They realized the fastest way to bypass the American monopoly was to simply give the models away.

And they didn’t just dump mid-tier toys. Their models are improving at a much higher pace compared to the American ones and have pretty much caught up in practical terms. They’ve consistently commoditized the technology that the US would love to leverage against us.

Autonomy through Proliferation

There is a profound irony here. China has long been known for its heavy domestic internet censorship and state oversight. Yet, they’ve inadvertently become the world’s greatest guarantor of decentralized, open-source AI infra.

By flooding the ecosystem with high-quality opensource models, they’ve made it functionally impossible for an authoritarian US government to lock down the future of software development.

Once a model like GLM 5.2 or Kimi K2.7 are on Hugging Face, downloaded, and running locally on hardware right here in Canada, the gates cannot be closed. It belongs to the global developer community. Better yet, it can be fine-tuned, quantized, and run entirely offline.

This isn’t about blind defence of the Chinese government or anything. It’s a pragmatic look at power dynamics: hegemony is the absolute enemy of innovation, and proliferation is the ultimate antidote to bullying.

When global superpowers compete by releasing open infrastructure, developers win. In fact, the aggressive opensourcing of Chinese frontier models may threaten the duopoly of Anthropic and OpenAI. OpenAI has already postponed their IPO, as companies start having trouble reconciling the costs of inference charged by these labs with whatever gains in productive they’re seeing from them.

Because Chinese labs chose to open up their models, the dream of an API-locked AI dystopia where Canada and other “middle powers” can be frozen out at the border is dead. We have choices, which means we have autonomy.

So, to the engineers and teams pushing the boundaries of open weights on the other side of the world, from a developer celebrating a complicated Canada Day: 谢谢你，中国。 You kept the future of AI open when our neighbours tried to lock it away.