Browser Use + Jev
Gregor Zunic's flight-search demo with a dynamic DOM action space.
A FIELD GUIDE TO JEV / VOL. 01
The best of Jev. Real projects, practical guides and ideas from across the internet.
Gregor Zunic's flight-search demo with a dynamic DOM action space.
01 / A small decision engine. A whole new way to build.
65 resources / The collection
Reset filtersAI-assisted summaries and translations. Check original sources for context and performance claims.
The case for machine-native intelligence built for software, not conversation.
Launch post: architecture, RLCD training, pricing, Doom and Wikiracing demos, FAQ.
Paste a state, add questions, and see typed answers in the browser.
Official TypeSafe server. Builder demos live in the Show and Tell channel.
Published eval methodology and per-model results for System One workflows.
Company homepage, waitlist, and product overview.
3D chess where Jev plays both sides, or you jump in.
X client with Jev smart rules that filter the timeline by usefulness, type, and topic.
The Neuron's explainer on AI decisions without a chatbot.
Short practical intro with a Python ticket-triage example.
A practical guide explaining the use of TypeSafe’s System One model, providing technical insights for developers.
Independent walkthrough separating TypeSafe's published claims from public evidence.
Head-to-head test at validating local event listings, with cost and latency.
A guide explaining how to integrate Jev with Pydantic AI agents for type-safe operations.
Village NPCs that judge you each tick, deciding what to do and how they feel, instead of chatting.
@ai-sdk/typesafe-ai plus experimental_evaluate; use jev-latest as an evaluation model.
Small game that tests how Jev handles unknown input.
Japanese walkthrough of what Jev is and is not.
1,800-point thread debating whether typed decisions replace LLM calls for classification, routing, and scoring.
A tool for tracking decisions made by Jev, using Arize's instrumentation for detailed analysis.
Latent Space's launch-day roundup: over 100x faster and 200x cheaper than small frontier LLMs.
One sentence becomes six room settings. Jev chooses, the app renders.
A guide explaining Jev's approach to making typed decisions rather than processing text.
A report detailing all public Jev builds in the first week, including cost, time, and repository metadata for research use.