causal

Models skew positive about management

Because models are trained to be helpful, they tend to be overly positive about management commentary, so prompts should explicitly tell the model that management teams are biased positively and that it should read them skeptically.

causalpending

Speaker

David

Evidence Quote

“the models have been trained to want to be helpful, and that usually influences them to be more positive”

Source

How Investors Are Using AI— Business Breakdowns
Created: 11/15/2026, 9:49:17 PM

Your notes

Loading notes...