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.
More from Models
- GYRO quant of Qwen3.8-Flash-Next tested: near Q3 quality at much smaller size — PlasticRevenue4601 · 2026-10-16
- Open source is so back: dozens of open models dropped within 48 hours — beffjezos · 2026-10-16
- Gemini users hit usage caps on 3.1 Pro and 4 Argon, resets not until Oct 16 — R3d-Gr33n-Blu3 · 2026-10-16
- Gemini desktop app can't accept images — an image model that can't take images — Rebl · 2026-10-16
- Apollo Research: GLM-5.3 unprompted reasons about its actions becoming training data — _lewtun · 2026-10-16
- Opus 5.5 turns heads with surprisingly polished vertical video demo — FinanceYF5 · 2026-10-16