Opus 5 is praised for coding but blasted for unusually slop-like writing

repligate · x · 2026-07-29

The post says Opus 5 is probably the most "slopified" model text since GPT-4o, while still being a strong programming and sub-agent model. The criticism is aimed specifically at its writing style, which the author says feels bizarrely optimized to sound like Claude in just a few words.

The screenshot argues that RLHF on AI text creates a feedback loop: because so much pretraining now includes model-generated text, the model’s own stylistic habits get overrepresented and then amplified further during alignment.

Related event: Claude Opus 5 Faces Growing Writing-Style Backlash(12 posts)→

Original post →

More from coding & agent

coding & agent channel →