TypeSafe claims Jev is 193x faster and 444x cheaper than an LLM
The post cites official figures: Jev makes a decision in 0.114 seconds versus 8.566 seconds for an LLM, costs $42 per billion input tokens, returns typed decisions with confidence scores, and has an open waitlist.
The numbers on this are absurd, and every one of them is the lab's own... TypeSafe puts Jev at 193.6x faster and 444.6x cheaper than an LLM on the same task. 0.114 seconds against 8.566. $42 per billion input tokens. it isn't a chatbot. it returns a typed decision with a calibrated confidence score, trained on RLCD instead of RLHF. early access, waitlist open. I already signed up. https://x.com/CompleteSkeptic/status/2099925682726002904/video/1