Calibrating Opus 5.5's stated confidence with Jev for position sizing
After finding that Opus 5.5's 88%-confidence trades actually won only 56% of the time, the author put Jev between the model and the market to map stated confidence to real win rates and apply half-Kelly sizing with a veto.
a friend who trades at one of the BIGGEST prop shops looked at my opus 5.5 setup for 30 seconds and asked one question: "where's your CALIBRATION?" i didn't have one. opus said 88% sure, so i sized like 88% sure. then i logged 3,000+ of its calls. its 88% trades win 56% of the time. LLM confidence is NOT probability. so now jev sits between opus and the market: → opus picks the DIRECTION + its confidence → jev maps stated confidence → REAL win rate → "says 0.88" → actually wins 0.56 → half kelly: ½ · (p - (1-p)/b) = 6% of book → VaR cap on top. VETO anything over in the video opus wanted 10x on btc. jev did the math and allowed 1x. same model. same signals. completely different RISK. if your agent sizes off its own confidence, you're betting 88% money on a 56% coin.
This post quotes another post: “Long read: how to build a Jev-powered agent stack”