Dev Complains LLMs Are Too Verbose, Calls for RL to Train Natural Language Output

sachdh · x · 2026-08-08

A developer highlighted a common frustration: today's large language models are extremely verbose, love jargon, and use confusing sentence structures in their responses.

This issue is reportedly worse in coding harnesses compared to consumer-facing products like ChatGPT. The original post urges AI labs to use Reinforcement Learning (RL) to train models to communicate more concisely, like a normal person would.

Original post →

Dev Complains LLMs Are Too Verbose, Calls for RL to Train Natural Language Output

More from Models