AI Summary
A recent study by Graphite analyzed the writing habits of various AI models, revealing distinct patterns that differentiate AI-generated text from human writing. The research found that while some previous indicators of AI writing have diminished, new telltale phrases and constructions persist across different models.
%22%2F%3E%3Crect%20width%3D%22800%22%20height%3D%22450%22%20fill%3D%22url(%23glow)%22%2F%3E%3Ctext%20x%3D%22400%22%20y%3D%22275%22%20text-anchor%3D%22middle%22%20fill%3D%22%2360a5fa%22%20font-family%3D%22system-ui%2C-apple-system%2Csans-serif%22%20font-size%3D%22132%22%20font-weight%3D%22800%22%20letter-spacing%3D%22-6%22%20opacity%3D%220.9%22%3Ecn%3C%2Ftext%3E%3Ctext%20x%3D%22400%22%20y%3D%22318%22%20text-anchor%3D%22middle%22%20fill%3D%22%2360a5fa%22%20font-family%3D%22system-ui%2C-apple-system%2Csans-serif%22%20font-size%3D%2211%22%20font-weight%3D%22600%22%20letter-spacing%3D%223%22%20opacity%3D%220.38%22%3ECONTEXT%20NEWS%3C%2Ftext%3E%3C%2Fsvg%3E)
- Researchers from Graphite examined the writing habits of AI models, identifying 13,000 phrases that are significantly more common in AI-generated content compared to human writing.
- Claude Opus 5.5 frequently uses the word 'dependable' and the phrase 'this matters,' appearing 116 times more often than in human samples.
- OpenAI's Astra model tends to use phrases like 'another dimension' and employs 'corrective framing' constructions more than 100 times more frequently than humans.
- Both Opus 5.5 and Astra have significantly reduced their use of em-dashes, with Opus 5.5 using it 99% less than human writing.
- Despite efforts to create more human-like writing, the overall number of tells remains consistent across different AI models, indicating challenges in completely eliminating these patterns.
- Graphite's findings suggest that while models may become more sophisticated, certain telltale phrases and constructions continue to emerge.
ai writingopus 5.5language modelstext generationdependability