The US didn’t need to support China joining the WTO and when it became clear that they were not being a good partner (keeping their domestic markets locked to outsiders, requiring tech and IP transfer, requiring domestic partners over 50%, violating international labor and environmental standards etc) they should have been expelled and their goods blocked from all markets that we could get to align.
That would have cut off a source of cheap production.
The lack of enforcement of the WTO agreement befuddles me. The result has been the polar opposite of these statements from President Clinton:
"Economically, this agreement is the equivalent of a one-way street. It requires China to open its markets—with a fifth of the world’s population, potentially the biggest markets in the world—to both our products and services in unprecedented new ways," said Clinton. In a speech in 2000, Clinton reiterated his hopes:
For the first time, our companies will be able to sell and distribute products in China made by workers here in America without being forced to relocate manufacturing to China, sell through the Chinese government, or transfer valuable technology—for the first time. We’ll be able to export products without exporting jobs."
But why is one company trying to do everything? Why do the intelligence vendors need to go into the app layer? Why did the go in to the coding tool layer? They could have let a rich ecosystem build around the API but they are killing start ups all over the place. Entire categories won’t get investment or traction because they are actively trying to be a monopoly
College is about the social network and interpersonal skills you build, it’s about mentorship from experts, it’s about an ecosystem of collaborative basic research. AI tutoring is only the factual learning none of the rest.
Unless your Claude code $20 comes with world class laboratory equipment good luck learning neuroscience or astronomy.
Hinton said we might be better off not building AI. He’s not stupid. Maybe run a thought experiment or two instead of assuming all new technology is inherently better.
Chemists and biologists stop lines of research at times when they present unreasonable risks. Why should this be any different?
I wonder if anthropic got word of or suspected LLM gateways were serving cheaper models and charging customers for higher cost models and keeping the difference, that seems like the only explanation for this
That usage probably comes from a couple of 200$ a month subscriptions. Hardware to run something that approaches frontier at acceptable speed is at least a million.
reply