š³This was a study I was waiting for: does appealing to the (non-existent) āemotionsā of LLMs make them perform better?
The answer is YES. Adding āthis is important for my careerā or āYou better be sureā to a prompt gives better answers, both objectively & subjectively! https://t.co/A4GeLKfYa5
Harvard study shows we can measure leadership skills by seeing how folks manage GPT-4o simulated people
AI assessments strongly correlate (r=0.81) with human team assessments. Effective leaders ask questions & do conversational turn-taking and have fluid & social intelligence https://t.co/R9M6Q0xlz0