Who's selling the data is the far more serious issue here. Behind this is a remarkably well-structured syndicate.
The supply chain looks something like this: consumer apps embed ad SDKs → those SDKs feed location signals into RTB ad exchanges → surveillance-oriented firms sit in the RTB pipeline and harvest bid request data even without winning auctions → that data flows to aggregators who don't have any direct relationship with consumers → and from there it's sold to government agencies, among others.
The genius of this structure is that accountability dissolves at every layer. Each intermediary can claim they're just passing along "commercially available data." Nobody verifies whether consumers actually consented to their location data being collected and resold. The consent verification is always someone else's job.
The real problem is that this data is buyable at all, by anyone, through an opaque multi-layered supply chain specifically designed so that no single entity bears responsibility for the end result.
In my corner of the world, average software developers at Tokyo companies, not that many people are actually using Claude Code for their day-to-day work yet. Their employers have rolled it out and actively encourage adoption, but nobody wants to change how they work.
This probably won't surprise anyone familiar with Japanese corporate culture: external pressure to boost productivity just doesn't land the same way here. People nod, and then keep doing what they've always done.
It's a strange scene to witness, but honestly, I'm grateful for it. I've also been watching plenty of developers elsewhere get their spirits genuinely crushed by coding agents, burning out chasing the slot machine the author describes. So for now, I'm thankful I still get to see this pastoral little landscape where people just... write their own code.