Jev's public demos: cost and latency for classification, email, search and compaction
Lists measured results from Jev's public demos: about $0.08 to classify 1,000 papers, about 3.5¢ for 500 emails, about 7 seconds for a flight search, and a ~1M-token Claude session compacted to ~86k, under a split where the LLM writes, Jev decides and code executes.
this JEV is certified f*cking diamond every agent you ship burns frontier tokens on questions that were never writing jobs is this spam? which worker goes next? is the draft good enough to show a human? those are decisions. Jev is built for that half of the loop you send state plus a typed question. it returns a choice, a score, or yes/no with confidence. no chat. no second opinion the public demos, not our lab: > ~1,000 papers classified for about $0.08, median around 256ms > ~500 emails in one inbox pass for about 3.5¢ > a flight search loop in about 7 seconds for about $0.0039 > a huge Claude session compacted from ~1M tokens down to ~86k in about a second the whole trick is the split if it creates, the LLM writes if it picks, scores, or gates, Jev decides if it does the thing, code does it pricing people quote: about $0.042 per million tokens in. output free. 10,000 decisions is about $0.42 a local router makes it obvious. goal plus what's already done. Jev picks research, write, or review. confidence under 0.85 goes to a human. the job lands as JSON in a folder. the writer never wakes up for a yes/no and the loop refuses to publish on its own drafts go to review. you hit post. Jev never sends the tweet one model writes. a cheaper one decides. nothing irreversible ships until a human says yes.
This post quotes another post: x.com/thegreatest_sv/status/2102802378378621355