LLMs lack artistic intent, and writing may resist outcome-based RL

teortaxesTex · x · 2026-09-22

teortaxesTex argues 'style' isn't the bottleneck: pretraining on code improved all tasks, and R1's math/code RL made it a far better writer than V3, so LLMs are good style imitators. The real gap is artistic intent — a task that may be hostile to outcome-based reward, unlike the logically structured training signals that generalize reasoning.

Related event: Why LLMs still can't write serious literature: no ground truth, no artistic intent(4 posts)→

Original post →

More from Models

Models channel →