Projects built with Jev

No projects found. Clear filters

MappityThe app is open source btw. You can play online with few prerecorded responses from Jev in the interactive demo, or you can grab the sources and run it locally with real data.

MappityFranci Penov

YouTube research at scaleVideo playing at 1x. Pulled transcripts for ~400 YouTube videos into my app, then let Jev loose on all of them to find which are worth building my next video on. 11 seconds, $0.004. 291 ruled out, 82 worth a look so we ranked those.Mario Jankovic

Vendor search by requirements227 vendors and their entire G2 payload. 19 questions buying spec. 10 seconds.  Jev is fast at vendor search.Rhys Fisher

Jev ReviewerIntroducing Jev Reviewer, a tool designed for systematic reviewers to quickly find and extract the information from research articles. App: GitHub:Ahmad Sofi-Mahmudi

Search a physical libraryJev lets me search my physical library by looking at the entire book index in parallel in 300ms. Here, the answer to “Who invented photography?” is probably on page 98 under "Niépce, Joseph Nicéphore"Seth Thompson

OCR-powered image classificationMade myself a little image classifier with OCR + Jev It was able to categorise ~900 images in 40 seconds Pretty coolFayaz Ahmed

Preflight personality simulationAdded Jev to Preflight a project im working on that simulates 1k+ personalities making human-like calls off public datasets. Jev’s killing it. Leading with Jev has boosted confidence at least 30% and responding in SECONDS.Hindrix

Scoring a frontier-AI essaywhat does jev from @typesafeai think of the pacing the frontier article by @DarioAmodei?Nicholas Dunzelman

News classification and geolocationThirty minutes of news. 2,782 articles. Jev classified every US headline in under 20 seconds for about five cents. Then canon geo sourced evidence for each data center site, with receipts. 1,303 US articles. 3 data center sites. 2 exact addresses.CMD+RVL

Paper Breakdown research recommendationsOrganically integrated JEV in a real project The Paper Breakdown Recommendation Engine We already had a working system that combines content-based and collaborative filtering. Pro users may now get additional curation with Jev. 0.0019$/user for ~70 recs 🤯 ~50 users in 5 secsAVB

Quality checks for physical-AI action labelsJev is insane. We are building egocentric training data for physical AI. Jev QA'd 58,643 action labels in under 3 minutes. 90 cents. A friction cost of the Claude & GPT models.Peter Wang