Kimi K3 passed a local medical-chart test with 25 identifiers masked
MaziyarPanahi · x · 2026-07-29
The author says he wrote 70+ skills for OpenMed and then handed one to Kimi K3. In a local Mac test, the model read a patient chart with 25 identifiers masked, no data leaving the machine, and still got every call right. The code and skills are open on Hugging Face.
More from coding & agent
- Tagvico 3.2.5 checks whether a selected model can really make the app’s tool calls — its_artur1 · 2026-07-29
- Caveman trims AI coding replies to fewer tokens without losing technical detail — KhuyenTran16 · 2026-07-29
- A microservice catalog test found Markdown, GraphRAG, and MCP graphs fail in different ways — JeremyCMorgan · 2026-07-29
- Composio benchmark finds similar success rates but wide speed gaps across coding harnesses — Teknium · 2026-07-29
- LLM APIs still disagree on the parameter name for output token limits — nuno6Varnish · 2026-07-29
- Open-source dashboard compares x402 and MPP across transactions, volume and users — kleffew94 · 2026-07-29