Claude Opus 5.5 Uses 95% Fewer Em Dashes, but Its Answers Are Getting Longer
6 Articles
6 Articles
BleepingComputer
cybernoz.comClaude Opus 5.5 uses 95% fewer em dashes, but its answers are getting longer
Anthropic's Claude Opus 5.5 appears to be changing how it writes, with new analysis showing fewer obvious AI writing patterns, shorter sentences, and simpler wording compared with Opus 5.
New versions of Claude are better equipped with code, mathematics, and complex reasoning, but as a result, their texts have become less natural and understandable to people.
Anthropic engineer explains why Claude's writing got worse although the model got smarter
Anthropic employee Jackson Kernion explains why newer Claude models write so oddly. Optimizing for math, code, and technical explanations aimed at other AI models has created a style that sounds like "overly-dense info dumps" to humans. Opus 5.5 tries to fix this, but Opus 4.6 remains unmatched as a pure writing model. The article Anthropic engineer explains why Claude's writing got worse although the model got smarter appeared first on The Deco…
Anthropic employee Jackson Kernion explains why newer Claude models write strangely: Optimization on math, code and technical explanations for other AI models has created a style that sounds "too dense and unnatural" for people. Opus 5.5 is supposed to counter, but Opus 4.6 remains unachieved as a pure writing model. The article Anthropic employee explains why Claude has forgotten to write for people first appeared on The Decoder.
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
