Generative AI makes it easy for me to translate my English writing into many different languages. It can’t help me understand how those translations come across to people who have spoken those languages since childhood.
When I see texts that have been translated into English by AI, I often wonder how the original authors feel. I imagine they want to know how native English readers experience their writing.
To explore that thought, I translated one of my blog posts into Italian using ChatGPT and CoPilot. I wanted to know how I’d feel about seeing my writing in another language.
I asked ChatGPT and CoPilot to create two versions. The first had to retain my natural voice and the second had to sound “natural” to an Italian native speaker.
Here are the final paragraphs of each translation.
CoPilot (prompt: retain my natural voice)
La consapevolezza di sé necessaria per evitare queste trappole può — e sarà — sviluppata nei contesti di lavoro. Nel frattempo, editor e altri professionisti dell’assicurazione qualità saranno lì a intercettare eventuali problemi.
CoPilot (prompt: sound natural to a native speaker)
La consapevolezza di sé necessaria per evitare queste trappole è qualcosa che può — e inevitabilmente verrà — sviluppato nei contesti di lavoro. Nel frattempo, editor e professionisti del controllo qualità svolgeranno un ruolo fondamentale nel intercettare eventuali problemi.
ChatGPT (prompt: retain my natural voice)
La consapevolezza di sé necessaria per evitare queste trappole può e verrà sviluppata nei luoghi di lavoro. Nel frattempo, editor e altri professionisti della qualità saranno presenti per intercettare eventuali problemi.
ChatGPT (prompt: sound natural to a native speaker)
La consapevolezza necessaria per evitare queste trappole si svilupperà — e in parte si sta già sviluppando — nei contesti lavorativi. Nel frattempo, editor e altri professionisti della qualità continueranno a vigilare, pronti a intercettare eventuali criticità.
My Italian is intermediate level, so I can’t tell whether any of these texts sound natural to a native speaker. I asked ChatGPT and CoPilot for an evaluation.
They both agreed that ChatGPT’s second translation sounded the most natural. CoPilot said it was more nuanced, made better use of idioms, and flowed better. ChatGPT said it sounded smoother, more polished, more idiomatic, and not as stiff as the other translations.
The problem here is that smoothness, polish, flow, and stiffness are not objective measures. For that matter, “natural” isn’t either.
The whole thing left me scratching my head. If I had to pick one of those paragraphs for real-world use, I’d have to choose the one preferred by ChatGPT and CoPilot. But I’d also be wondering how much I could rely on their judgement, as it is built on so many subjective ideas.
I also can’t tell which of the two other translations retains my natural voice, so I turned to CoPilot for advice. It said that ChatGPT’s translation sounds like the voice of an institutional authority.
“A formal, institutional, and forward-looking voice that communicates ideas with measured authority, emphasizing systems, professional oversight, and gradual improvement.”
CoPilot said its own translation sounds more reflective and provides professional reassurance.
“A reflective, professionally grounded voice that combines analytical clarity with a reassuring, process-oriented perspective, using slightly elevated but controlled language to convey authority and calm confidence.”
I don’t think the original English blog post sounds institutional (although again it is a subjective measure). Clearly, something has appeared in ChatGPT’s Italian translation that wasn’t in the English.
(Of course, an English institutional voice can’t be directly translated into Italian because the two languages are so different. This is a level of translation that requires a human. Banks do not sound the same in English and Italian!)
I carried out this experiment because I wanted to explore how writers feel when they see their work translated into English by AI. I imagine that many end up feeling very frustrated.
My key frustration points in this experiment were that I could not stress test or verify the AI outputs.
If this had been a real-world situation, my best solution would’ve been to ask an Italian human being!
Tide & Time Editorial 