AI slop benchmark shows Claude Code replies are the worst writing offenders
rms80 · x · 2026-11-10
A new benchmark on AI slop finds AI writing obscures main ideas and invents awkward phrases, violating established English writing principles far more often than human writing — with Claude Code replies the worst offenders. Commenters push further: could a communication-clarity benchmark extend beyond short utterances, and is a scaled 'theory of mind' really out of reach?
Related event: AI Writing Benchmark Finds Claude Code Replies Full of Vague Phrasing(2 posts)→
More from Models
- pyannote speaker-diarization-3.1 trends on Hugging Face — pyannote · 2026-11-10
- Fable 5.2 draws every pixel via code — no diffusion, no 3D, no render engine — DimitrisPapail · 2026-11-10
- Vibe-coded Google Earth in JavaFX shows Gemini 3.8 Flash is the best free workhorse — AnahataASI · 2026-11-10
- Gemini 4 Carbon goes live in Google AI Studio, requires Ultra plan or API key — cedric_chee · 2026-11-10
- Cutting GPU power 42% costs nothing: RTX 3080 Ti runs Qwen 3.5 9B at full speed on 250W — Asthenia5 · 2026-11-10
- Pelican meme math: past 200k tokens, long-context agent work stays on Luna — petrusenko_max · 2026-11-10