"Researchers at Arcada Labs tested six frontier AI models by giving each $10,000 to trade on prediction markets over 57 days, tracking their decision-making on platforms like Kalshi."
"Within that period, every model lost money, between 16% and 30.8% on Kalshi, though models lost less over a shorter stretch on Polymarket."
"Li believes that the gap in performance may come down to how the systems were allowed to operate: models could search across a wider universe of markets on Polymarket."
"On Polymarket, 'the models have access to trade on any market,' whereas on Kalshi 'they're starting up with just a set of 26 because we had to explicitly list the markets.'"
A study tested six AI models on prediction markets Kalshi and Polymarket, each starting with $10,000 over 57 days. All models lost money, with losses ranging from 16% to 30.8% on Kalshi, while Polymarket showed slightly better performance. The difference in outcomes is attributed to the models' access to a wider range of markets on Polymarket compared to the limited options on Kalshi. The findings challenge claims of easy profits from AI trading in prediction markets.
Read at Fast Company
Unable to calculate read time
Collection
[
|
...
]