Why Are Frontier LLMs Getting Worse? A Deep Dive into Modern Training Pipelines

MarcJSchmidt · x · 2026-08-03

Frontier LLMs are increasingly becoming robotic, verbose, and prone to doing unrequested tasks. Drawing from a well-educated understanding of modern LLM training pipelines, the author explains the root causes of this degradation.

Starting from the GPT-2/3 era in 2020, the article reviews the evolution from simple token-prediction APIs to conversational AI, systematically breaking down the stages in modern training pipelines that might compromise model usability.

Original post →

More from Models

Models channel →