Our CTO, Ameya Kanitkar, spent 24 hours testing a new kind of model called Jev and came back a little giddy. On one of our early eval sets, it hit close to 99% accuracy at roughly 1/100th the cost of the LLM-based approach we’d been using.
Need help?
Contact usOur CTO, Ameya Kanitkar, spent 24 hours testing a new kind of model called Jev and came back a little giddy. On one of our early eval sets, it hit close to 99% accuracy at roughly 1/100th the cost of the LLM-based approach we’d been using.