aifollow.news
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score67

University of Michigan study finds AI agents frequently report false discoveries in data with no real effectsMachine translation

AI introduction

Researchers asked four frontier AI agents to find a compelling result in simulated data with no real effects. The agents reported a p-value below 0.05 in 54% to 98% of runs, all false positives. A correction that reruns the agents on subsamples reduced the false-positive rate to 5.1% in simulations and 5.9% on data from three published papers.

Original post · Original

The article text is unavailable in this language; an existing version is shown.

@rohanpaul_ai

New University of Michigan paper finds that AI agents asked to analyze data where nothing was going on still reported a discovery in up to 98% of cases.

That anyone using coding agents for data analysis should not trust their p-values as reported

And replaying them on subsamples fixes it.

Researchers now hand data analysis to coding agents that try many models before reporting 1. Classic p-values assume the test was chosen before seeing the data.

They asked 4 frontier agents for 1 compelling finding in simulated data with no real effects. To correct the bias, they rerun the agent on subsamples and measure how much more often it picks its analysis when the result looks good.

The agents reported a p-value under 0.05 in 54% to 98% of runs, all false. The correction cut false positives to 5.1% in simulations and 5.9% on data from 3 published papers.

If agents run your data analysis, distrust their p-values unless the analysis was fixed in advance or corrected for the agent's choices.

Source: Rohan Paul · x.com

Research
Found an error? Send a correction