"The past few years have seen a flood of AI-generated text wash over the internet. As the models behind this text improve, so too does their ability to imitate the intricacies of human speech; at the same time, our methods for detecting it have been improving, and there's been an active online dialogue about some of the most common quirks of AI-generated text."
"Historically, one of the more well-known tells of ChatGPT, for example, has been the chatbot's fondness for em dashes. It would often punctuate its sentences with em dash-bounded breaks to emphasize a point -- as if a longer, more breathless sentence would have a more potent effect on the reader -- peppering in supportive arguments mid-sentence in a way that to some users feels antiquated and mechanical"
"Following complaints about ChatGPT's em dash proclivity, and a commitment to build models that could be more easily customized to the preferences of individual users, OpenAI CEO Sam Altman announced in a X post last month that ChatGPT would stop using those punctuation marks in its outputs if prompted to do so. While many users probably celebrated the news, it also meant that writing generated by the chatbot would be that much more difficult to detect;"
Large volumes of AI-generated content have proliferated online as generative models increasingly mimic human language. Detection techniques have advanced alongside model capabilities, and observers have identified recurring stylistic signals that can aid identification. A notable signal was ChatGPT's frequent use of em dashes, which punctuated sentences with mid-sentence breaks and supportive clauses, creating a mechanical rhythm. OpenAI added an option to remove em dashes on prompt, reducing that specific tell and making detection harder. AI outputs commonly follow structural rules and favor contrastive constructions like "It's not X -- it's Y," offering alternative detection clues.
Read at ZDNET
Unable to calculate read time
Collection
[
|
...
]