Awesome Jev: early projects and use cases
A community-curated list gathers early Jev projects and ideas for developers who already have API access.
Jev vs GPT-5.4 on hard fact-checks: no significant edge in rerun, at 1/50 cost
A community rerun of hard fact-check benchmarks finds Jev and GPT-5.4 statistically indistinguishable (3.3-point gap), while Jev costs about a fiftieth as much.
I said Jev beat GPT-5.4 on hard fact-checks by 11.1 points. That was one run. Rerun five times, I can't tell them apart: 3.3 points, not significant. Jev costs a fiftieth as much. Raw runs: https://github.com/TheWayWithin/jev-bench… https://jamiewatters.work/journey/jev-ties-gpt-5-4…
· 0 likesOpen on X
More like this
Training an MLP on Qwen 4B to Replicate Jev Behavior
The author shares an open-source project openjev that trains an MLP on qwen 4b to work like Jev, with a Hugging Face link. Link
Swapping an agent's tool-calling reasoning with Jev
The author shares replacing an agent's tool-calling reasoning with Jev, using Fable, Astra, and Opus; early results show drastic savings with very close results, with a demo video promised.
