ChatGPT took on 160 human forecasters in a secret prediction game and landed in a baffling spot
Briefly

ChatGPT took on 160 human forecasters in a secret prediction game and landed in a baffling spot
"The ability to forecast the future is a valuable sign of intelligence and a good test of AI's capabilities. How good is ChatGPT at prediction? An answer to this fascinating question emerged recently when economist David Seif wrapped up an annual forecasting contest he runs for a secret group of economists, hedge fund investors, and tech executives. In its seventh year, the challenge requires contestants to predict roughly 30 events."
"These are complex rules, covering multiple pages. Contestants must assign a percentage based on the likelihood of each event happening. As the results come in over the year, these predictions are scored a bit like golf. The lowest score wins. "You get points equal to the square of the difference between what you put and the results," Seif said. For example, if you assign a 90% chance of something happening and you get it right, you get 10 points."
An annual forecasting contest required contestants to assign percentage probabilities for roughly 30 events across politics, business, science, economics, pop culture, and sports. Contest predictions are scored by squaring the difference between the assigned probability and the outcome, with the lowest cumulative score winning. A 90% probability that occurs yields 100 points; if it fails, the squared 90-point error yields 8,100 points. A hedge-fund director, Sam Leffell, entered ChatGPT by pasting the contest's multi-page rules into the model to generate probability forecasts for specific prompts such as a celebrity engagement and a country's euro adoption.
Read at Business Insider
Unable to calculate read time
[
|
]