Skip to content
Artwork for Machine Learning Tech Brief By HackerNoon
Machine Learning Tech Brief By HackerNoon · October 1 · 3 min

Claude Opus 5.5 Writes With 17% Shorter Sentences: How It Reads More Human

This story was originally published on HackerNoon at: https://hackernoon.com/claude-opus-55-writes-with-17percent-shorter-sentences-how-it-reads-more-human. Screening text for em dashes now waves most Opus 5.5 answers through, and the count worth watching has moved to words like "perhaps." Check more stories related to machine-learning at: https://hackernoon.com/c/machine-learning. You can also check exclusive content about #claude, #anthropic, #llm, #ai-writing, #claude-opus-5.5, #ai-content, #ai-human-likeness-metric, #claude-opus-test, and more. This story was written by: @khasky. Learn more about this writer by checking @khasky's about page, and for more stories, please visit hackernoon.com. In the Opus 5 answers, the em dash appeared 15.2 times per 1,000 words. Opus 5.5 brought that down to 0.8, about 95% fewer. Semicolons followed a smaller slide, from 6.10 to 1.64 per 1,000 words, which works out to about 73% fewer.

0:00-3:27

transcript

No transcript — this publisher did not publish one.

show notes

This story was originally published on HackerNoon at: https://hackernoon.com/claude-opus-55-writes-with-17percent-shorter-sentences-how-it-reads-more-human.
Screening text for em dashes now waves most Opus 5.5 answers through, and the count worth watching has moved to words like "perhaps."
Check more stories related to machine-learning at: https://hackernoon.com/c/machine-learning. You can also check exclusive content about #claude, #anthropic, #llm, #ai-writing, #claude-opus-5.5, #ai-content, #ai-human-likeness-metric, #claude-opus-test, and more.

This story was written by: @khasky. Learn more about this writer by checking @khasky's about page, and for more stories, please visit hackernoon.com.

In the Opus 5 answers, the em dash appeared 15.2 times per 1,000 words. Opus 5.5 brought that down to 0.8, about 95% fewer. Semicolons followed a smaller slide, from 6.10 to 1.64 per 1,000 words, which works out to about 73% fewer.

links13