Remove the score-rating lines and 'Claude slop' detection jumps to 100%
TuhinChakr · x · 2026-11-07
Tuhin Chakrabartry endorses @nsaphra's finding about 'Claude slop' in review texts. The concrete measurement: raw AI-detection runs 95%, but after removing the lines containing specific score ratings, every sample hits 100% — the remaining text is almost entirely model-generated boilerplate, with the score lines merely diluting the detection signal.
More from Models
- Meta rolls out Muse Wonder-derived specialized models to Muse and Meta AI: 2.4x less forgetting — mhdfaran · 2026-11-07
- Meta ships Muse Wonder specialized models: 2.4x less forgetting, 67% better unsticking — AIatMeta · 2026-11-07
- Generated worlds tested at runtime: local interactions 83/100, stateful workflows just 30/100 — nptacek · 2026-11-07
- Steering a single neuron gives Qwen3-30B a new identity in ~1-2% of replies — Sauers_ · 2026-11-07
- OpenAI and Anthropic stuck in a release standoff as both hold back their next models — kimmonismus · 2026-11-07
- Deep Learning Weekly #480 ships with 'Gemini 4 Carbon' mention and model-routing paper — dl_weekly · 2026-11-07