Top AI Product

Yangzhi Zhu’s team at Terasaki Institute for Biomedical Innovation shipped a contact lens that tracks intraocular pressure and dispenses glaucoma drugs on its own — entirely through polymer microfluidics. No silicon inside the lens. Science Translational Medicine published it this month, and it hit Hacker News front page and Hackaday the same week.

How the hardware works

Everything is soft polymer with microscopic fluid channels running through it. When IOP climbs, the cornea bulges a hair and physically squeezes pressure-activated reservoirs inside the lens. Those reservoirs hold a silk sponge that soaks up 2,700x its weight in drug — loaded with timolol and brimonidine so far. No pumps, no electronics, no user input. Validated in artificial eyes, ex vivo cow eyes, and live hypertensive rabbits. Zhu’s pitch: patients forget to dose, the lens doesn’t.

Phone-side neural net as the API

The readout is where developers come in. A smartphone camera watches the lens and a neural net reads visual features to back out the IOP number — the electronics live in your pocket, not your eye. That inference pipeline is the natural API surface. Pipe daily IOP into Apple Health, hand it to a health agent for long-term trend monitoring, fire reminders when the curve drifts before the drug reservoir kicks in. Closed loop on the eye, open API on the phone.

You Might Also Like

• Mcp2cli the Tool That Cuts mcp Token Costs by 99 Just hit Hacker News
• 685 Hacker News Upvotes in one day why Canirun ai Struck a Nerve With Local ai Enthusiasts
• Claude Channels Scores 375 Points on Hacker News Anthropics Play to Replace Openclaw
• George Hotz Wants to Sell you a 12000 ai Supercomputer and 221 Hacker News Comments Cant Stop Arguing About it
• Ensu got 328 Points on Hacker News the Privacy Crowd Wants ai That Never Phones Home