AI Writing Benchmark Finds Claude Code Replies Full of Vague Phrasing

A benchmark study by developer zhizdev finds that AI-generated writing often obscures meaning with vague phrasing and awkward coinages, with Claude Code replies showing vague wording in 60% of cases, far above human levels.

2026-11-10 ~ 2026-11-10 · 2 related posts

• AI writing benchmark finds Claude Code replies use vague wording 60% of the time vs 4% for humans — IanArawjo · 2026-11-10
• AI slop benchmark shows Claude Code replies are the worst writing offenders — rms80 · 2026-11-10