Opus 5.5 loves to tell you ‘this matters’ (and other AI writing tells)
By Russell Brandom · Oct 1, 2026, 12:50 PM CDT
Opus 5.5’s biggest tell is the word “dependable,” which pops up 23 times more often than in human samples.
Excerpt shown under fair-use limits. Full text remains with the original publisher.
People in this coverage
Explore their history and attributable record. Being mentioned does not imply endorsement.
Layer 1 · Claims & fact checks
AI analysisLayer 3 · Reporting analysis
AI analysisWord choice emphasisThe article highlights a single word as a diagnostic marker, using a quantitative‑sounding figure to lend authority.
Appeal to authorityThe claim is presented as a definitive characteristic of the AI model without providing a source, creating an impression of expert knowledge.
Context
AI analysisMissing context
The article provides no information about how the frequency was measured, what corpus of human samples was used for comparison, the size of the dataset, the statistical methods applied, or whether the difference is statistically significant.
Important context
Understanding AI‑generated‑text detection requires details about the methodology, sample selection, and validation of any linguistic markers claimed to be distinctive.
Opinion vs. reporting
AI analysisThe piece presents a claim about word frequency as a factual finding without citing any study or data, making it more opinion or speculation than verified reporting.