so we started an experiment this week. every few days we take one of the biggest markets on polymarket thats about to expire, ask chatgpt, claude, gemini and grok to commit to a call before it resolves, then score every model when it does. no hedging, one call each with reasoning and a confidence number, locked in public before resolution.
first two markets are in. the fed decision next week, market prices 75% no change, all four models said hold, though confidence ranged from 72 to 86. and strait of hormuz shipping back to normal by july 31, market says 1%, all four said no. the highlight was claude, which has no live web access, still getting there on pure insurance and rerouting logic.
so far the models just agree with the market, which honestly makes sense, both are consensus machines digesting similar information. the interesting day is when they split from the market or from each other. thats when we learn whether four AIs reading the same world can see something the money doesnt.
what markets would you want them to call? looking for good ones expiring in the next week or two.
[link] [comments]