The Economist: ‘How to Spot AI Writing’
The Economist (gift link): You can discover AI’s hallmarks by comparing the writing of man and machine. To do this you need a baseline that is distinctive and familiar. The Economist turned to prose that we’re sure is human and that readers will recognise: our own. We designed a study to ask top LLMs — OpenAI’s ChatGPT, Anthropic’s Claude, Google’s Gemini and xAI’s Grok-to write versions of our…
The Economist conducted a study to identify key characteristics of artificial intelligence (AI) writing, comparing it to human-authored texts. They utilized four leading large language models (LLMs) – OpenAI’s ChatGPT, Anthropic’s Claude, Google’s Gemini, and xAI’s Grok – to generate versions of The Economist’s articles without web research.
The researchers compared 55,940 sentences and 1.2 million words of human and AI-written content. To minimize the influence of their own journalism, they also analyzed texts from CNN, the New York Times, and the Washington Post. Additionally, novel excerpts from 1950 to 2022 served as a further test.
The study revealed that AI prose can be distinguished by word and punctuation selection, as well as sentence and paragraph structure. However, the hallmarks of AI writing are not what one might assume, largely because AI writing styles have evolved with software updates. This shift in style does not imply that LLMs are excellent writers; in fact, their prose tends to be unclear, lacking elegance, and often formulaic.
For those aiming to be exceptional human storytellers, it is advisable to steer clear of certain peculiarities present in AI-generated writing.
Written by urgent.news from Daring Fireball's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
Also reported by 1 other outlet
- The Economist: ‘How to Spot AI Writing’ economist.com
