Perplexity's new model pplx-decider v1.1 got 643 of 669 medical test calls right, outperforming the paid Jev model while costing about 43% less to run. It's free to download.
Perplexity's new decision model, pplx-decider v1.1, got 643 of 669 test medical calls right, things like who needs urgent care and which diagnosis code fits. That beats Jev, a paid model built for the same job, and costs about 43% less to run. It's free to download, so a
During live clinical consultations, an ambient scribe periodically feeds transcripts to Jev, which traverses a medical ontology to classify symptoms, update the differential diagnosis, suggest treatments, and flag red flags in real time.
The author demonstrates how to triage a patient to the right doctor using only TypeSafe AI's Jev model and some question-asking code, noting that no LLM is used during the conversation.
A developer shares building a calorie tracking app with Jev, highlighting its instant experience.
