Google hired pro writers to copyedit Gemini 4 Argon; prose hits grade 10.64 reading level
every · x · 2026-10-14
Every reports Google DeepMind hired professional writers to copyedit Gemini 4 Argon's answers and write 'golden examples', targeting AI-isms like 'load-bearing', 'in a world', and reflexive bullet lists. On a 20-prompt writing benchmark, Argon's prose averaged a 10.64-grade reading level vs the 7th–8th grade of most frontier models — denser, not necessarily better. Advice: use it as an editor to untangle structure, not a one-shot ghostwriter.
More from Models
- Opus 5.5 still leads a month later, but open-weight decision models are closing in — airesearch12 · 2026-10-16
- Google restricts Gemini Pro access for Google Plus subscribers, matching free tier — EmergencyLess8861 · 2026-10-16
- Meta releases Muse Spark Open, trained with vLLM-powered RL inference from day one — colinmcnamara · 2026-10-16
- Meta open-sources Muse Spark: runs on two Mac Studios, license bans passing output off as human-written — mawcopolow · 2026-10-16
- Golden Gate Claude explainer resurfaces: interpretability premise still holds — HarperSCarroll · 2026-10-16
- Hugging Face livestreams release of a new open-weight model — huggingface · 2026-10-16