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)→
More from coding & agent
- theo builds his own visualizer for today's agent models, showing how cheap Luna really is — ivan_bezdomny · 2026-09-23
- Vite+ Hits RC: One Rust-Powered CLI to Replace Your Entire Web Toolchain — cnakazawa · 2026-09-23
- Tesla's in-car Grok agent books trips across Gmail, Calendar and Notion in one command — xiaohu · 2026-09-23
- Tesla's In-Car Grok Assistant Now Executes Cross-App Tasks in One Sentence — xiaohu · 2026-09-23
- Garry Tan says Capy lets him ship PRs much faster than Codex or Claude Code — garrytan · 2026-09-23
- DeskPilot: open-source native Python desktop client for local LLMs with MCP and sandboxed tools — poofph · 2026-09-23