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 Experiment: GPT-4-Era Prompting, Very Low Cost, Tuning with Astra
A user shares learnings from an experiment with Jev: it requires explicit prompting like older GPT-4-level models, is very cheap, and they tuned it for about 8 hours with Astra.
A few learnings from this experiment: - Jev feels like a throwback to GPT-4-level "dumb", where you need to prompt a lot of things explicitly. (e.g. 'kill when you are fully isolated for the last 5 seconds') - Insanely cheap $: Let Astra run with it to tune for like 8h, and it
· 1 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.
