Post-training gives LLMs a distinct voice, making outputs detectable

TuhinChakr · x · 2026-08-20

This post cites Bradley Emi, arguing that post-training is what gives Large Language Models (LLMs) their distinct "voice." As long as post-training exists, model outputs will remain detectable, implying that evading AI detection tools may be fundamentally difficult due to the stylistic imprint left by the post-training process.

Original post →

More from Models

Models channel →