
蘋果書寫工具整合於LINE,支援改寫、校對與語氣轉換,且可透過「描述更動」呼叫ChatGPT生成內容,僅限支援Apple Intelligence的iPhone 15 Pro系列及更新機型使用。
AI-generated summary
蘋果書寫工具是Apple Intelligence功能的一部分,僅在支援該功能的iPhone機型上可用,可協助使用者改寫、校對與調整文字語氣。
蘋果書寫工具功能可在LINE中直接請AI代筆,不用跳出去其他App。(圖/本報製圖)
不少人每天都在LINE聊天,但可能沒發現,iPhone其實早就能直接用AI幫忙改寫訊息。只要使用支援Apple Intelligence的機型,在LINE聊天室輸入文字後,就能叫出「書寫工具」,例如幫忙把原本的句子改得更客氣、更專業,甚至直接換一種語氣。
對經常用LINE工作或聊天的人來說,這項功能其實相當實用。像是臨時要回主管訊息,覺得原本語氣太直接;或是和朋友、客戶溝通時,不知道一句話怎麼寫比較不尷尬,都可以先把內容打好,再交給AI潤飾,不用另外跳到ChatGPT、Gemini等App來回複製貼上。
請繼續往下閱讀...
LINE訊息直接叫AI幫你改
使用方式很簡單,在LINE聊天室輸入訊息文字,再選取文字,就能叫出「書寫工具」。接著可以選擇「改寫」,或切換成「平易近人」、「專業」、「簡潔」等不同語氣;如果只是擔心有錯字,也能使用「校對」,讓AI幫忙檢查。
蘋果也提供「描述更動」功能,用戶可以直接告訴AI想怎麼修改,例如輸入「幫我寫得委婉一點」、「改得正式一點」,再交給書寫工具重新整理。
● 實測跟長官請假訊息改寫
從LINE打字框可直接叫出書寫工具。
書寫工具提供改寫、校對和轉化語氣等功能。
例如跟長官的道歉文,選擇專業語氣改寫。
完全沒想法也能讓AI代勞
如果對訊息內容完全沒有想法,也可以把整件事直接交給AI。舉例來說,在LINE輸入框叫出「書寫工具」後,透過「描述更動」輸入「幫我寫一封給女友的道歉訊息」,系統會進一步串接ChatGPT協助產生內容。ChatGPT也可能繼續詢問更多細節,例如對方名字、吵架原因,或希望傳達什麼結果,再依照提供的資訊產生更完整的文字。
這也就是說,不只已經寫好的LINE訊息可以交給AI修改,就連不知道該怎麼開口時,也能直接請AI幫忙起草。
● 實測請AI直接草稿給女友的道歉訊息
輸入需求,可以直接請AI草稿訊息,例如輸入「給女友的道歉文」。
會直接轉到ChatGPT,不用離開LINE。
ChatGPT會額外訊問細節。
AI馬上寫好道歉文。
不過,這並不是LINE推出的新功能,而是Apple Intelligence內建的「書寫工具」。這項功能除了可在備忘錄、郵件等蘋果內建App使用,也能在部分第三方App中使用,只要是在可以輸入文字的地方,就有機會直接使用。
哪些iPhone可用?
唯一要注意的是,「書寫工具」屬於Apple Intelligence功能,因此iPhone本身必須支援Apple Intelligence才行,從iPhone 15 Pro系列開始才能使用Apple Intelligence。
iPhone支援Apple Intelligence機型一次看
● iPhone 18 Pro系列、iPhone Duo
● iPhone 17系列、iPhone Air、iPhone 17e
● iPhone 16系列、iPhone 16e
● iPhone 15 Pro系列
《你可能還想看》
iPhone省電別做錯!這5大功能千萬別亂關 達人揭後果

Research from the State University of Campinas in Brazil found that chatbots will adjust their political judgments when faced with users with different political views, acting like "ideological chameleons" and potentially exacerbating social polarization, while the public often mistakenly believes that AI is objective.

Deutsche Welle asked nine artificial intelligence models to name the 2026 Nobel Prize winners. Most AIs pointed to GLP-1 developers for the Medicine Prize, Can Xue for the Literature Prize, and Liu Ruqian for the Chemistry Prize, but they also exposed information limitations and low-level errors.

U.S. Treasury Secretary Bessent said that the United States and China are discussing the establishment of an emergency notification mechanism for artificial intelligence accidents to deal with data transfer incidents similar to those involving the Chinese AI model Kimi. He mentioned the discussion on AI security issues with He Lifeng, Vice Premier of the State Council of China, and cited the Anthropic report alleging that Dark Side of the Moon forwarded user requests to the Claude model through fake accounts, involving military surveillance image analysis and model distillation.
Xikou Town, Fenghua District, Ningbo City, Zhejiang Province and other places have realized the intelligent upgrade of cultural tourism scenes through technological means such as AI glasses and the intelligent "Feng Xiaotao", promoting the transition from one-way explanation to two-way interaction, activating county cultural tourism resources, and forming a differentiated development path.

A survey by the Oriental Online Consumer Research Group shows that 90.6% of Taiwanese users regard network stability as their primary consideration, higher than 86.9% of download speed. With the popularity of Internet access by multiple people and devices, cloud backup and AI applications, Wi-Fi dead spots, unstable connections and upload speed requirements have become new focuses. The traditional evaluation criteria based on download speed are changing.

Experts urge Hong Kong to implement data governance and safety standards for AI to ensure responsible use, define liability boundaries, and address cyber-enabled crimes such as scams and money laundering using deepfakes, as police identify AI as a major cyber threat in 2026.