Urgent.News

What's breaking now, across thousands of outlets.

AI

No need to draw blood, just one drop of sweat… Korea University develops ‘AI skin patch’ to track drugs in the body

Translated from Korean Read in Korean

Researchers at Korea University have developed a technology that uses a thin skin patch to track the concentration and breakdown of drugs in the body through sweat. The patch, which does not require blood sampling, can be used for personalized medication management and doping tests for athletes. In a study involving 10 adults, the researchers used the patch to track changes in sweat metabolites after consuming caffeine, and were able to detect individual differences in caffeine breakdown rates.

The technology uses a gold nano-gel patch and AI algorithm to analyze sweat signals and calculate drug concentrations.

Written by urgent.news from Hankyoreh's report — not a translation of it. Machine-written — may contain errors; check the original before relying on it.

Also reported by 1 other outlet

Read the original at hani.co.kr →

More in AI

MCP Debate: Token Tax, Context Bloat, and What Devs Can Do

TL;DR: A post on maharship.com argues MCP was designed for 2024-era models and now causes context bloat and a token tax, sparking a ~165-point Hacker News thread with 100+ comments and pushback on X.

  • MCP introduced in 2024 leads to context bloat and token tax on modern models.
  • Debate on maharship.com sparks heated discussion with over 165 points and 100+ comments.

06 — Chat Works. Does the Agent Actually Retrieve Memory?

The images in this article are explanatory diagrams with Chinese labels, not screenshots of test results. Each caption summarizes the diagram in English.

  • Initial tests showed memory content in conversation context
  • Active retrieval failed despite functional server read path
  • Missing configuration field caused active retrieval issues

More from Tuesday 22 September →