Fine-tuning large language models on domain-specific data degrades their generality and ability to engage in open-ended conversation, so enterprise applications should use prompt engineering and in-context learning with base models rather than fine-tuning, which trades away the 'magic' of generality

factualpending

Speaker

Arvin Shabos

Evidence Quote

“the moment you start fine-tuning it for a specific vertical...it just stops having that old magic it cannot Converse in a more General way”

Source

Perplexity CEO: Disrupting Google Search with AI— The Logan Bartlett Show
Created: 8/11/2026, 1:25:03 AM

Your notes

Loading notes...