LLMs could write like humans but post-training guardrails make their text detectable

LLMs don't write in a recognizable style because they can't do better. Post-training and safety guardrails sharply narrow their expressive range, argues Pangram CTO Bradley Emi. Base models without these constraints already write with far more variety. The article LLMs could write like humans but…

LLMs don't write in a recognizable style because they can't do better. Post-training and safety guardrails sharply narrow their expressive range, argues Pangram CTO Bradley Emi. Base models without these constraints already write with far more variety. The article LLMs could write like humans but post-training guardrails make their text detectable appeared first on The Decoder.

Source: The Decoder — Published August 20, 2026 at 17:36 UTC — Category: Models