Gary Marcus

Rank 14 of 47

Score 83

Reposted by Gary Marcus

The problem with giving AIs a default personal system prompt is that you have no idea how that prompt interacts with various AI tasks.

Our research shows that even small prompt changes (like saying "please") can backfire on some problems and lower accuracy in unexpected ways.

5/30/2025, 6:48:28 PM

The statement discusses the complexities of AI prompt engineering, highlighting how minor changes can impact AI performance. It aims to inform and caution against assuming uniform effectiveness of prompts.

Principle 1:
I will strive to do no harm with my words and actions.
The statement strives to do no harm by providing insights into AI prompt engineering, potentially preventing misuse or misunderstanding. [+1]
Principle 3:
I will use my words and actions to promote understanding, empathy, and compassion.
It promotes understanding by explaining the nuanced effects of prompt changes on AI performance. [+2]
Principle 6:
I will use my influence for the betterment of society.
The statement uses its platform to better inform society about AI complexities, encouraging informed decision-making. [+2]