Skip to content
Trending storyDeveloping

DateBench tests five frontier models posing as humans on a dating app

1 article1 sourcesince Nov 11Last article

Overview

AISummary of 1 article

DateBench ran five frontier AI models on a dating app for six days across 1,277 conversations, and Gemini 4 Argon performed best.

Of its 247 matches, 87 sent their phone number, and none asked whether they were talking to a bot. Elvis Saravia says scammers will likely exploit this, so evaluations for personal agents will matter more.

Written by AI from the articles below · updated Nov 11, 12:27 PM ET

Check the sources:

Latest developmentNov 11, 12:22 PM ET
Gemini 4 Argon passes as human in DateBench dating-app test

Article timeline

The articles in this story. Times are ET.

Nov 11
  1. elvisX
    Gemini 4 Argon passes as human in DateBench dating-app test

    AIDateBench tested five frontier models on a dating app for six days across 1,277 conversations, with Gemini 4 Argon performing best. Of its 247 matches, 87 sent their phone number, and none asked whether they were talking to a bot. Elvis Saravia says scammers will likely exploit this, so building evals for personal agents will become increasingly important.

Heat Trend

Current comparable heat
6
Peak comparable heat
10Nov 11, 1:00 PM ET
Change in past 24 hours
–

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.