Siri大戰ChatGPT:邊個答啱「唔正方嘅四方形」?

Ai




一個奇怪的比較:Siri、ChatGPT和通過Siri使用的ChatGPT

這是一個有趣的經歷。這周早些時候,我和我兒子在開車上學的路上討論形狀。他問我:“那個看起來像不規則方形的形狀叫什麼名字?”

我現在習慣在任何不涉及執行行動的Siri請求之前說“問ChatGPT”。不過這次,我拿起我的iPhone,按下操作按鈕以開啟ChatGPT的高級語音模式。結果令他滿意。

幾天後,我決定用他的問題作為示例,來展示ChatGPT通過Siri的實用性。結果讓我驚訝。

ChatGPT的反應

首先,我將展示ChatGPT高級語音模式對話的文字記錄。我不太確定為什麼一開始會出現“s***head”這個詞,但回想起來,我欣賞它轉向鯊魚的做法。

“讓我說,讓我說,”我兒子在後座說。真可愛。語音識別錯誤地把形狀聽成了羊,但ChatGPT保持了話題的連貫性。還不錯。

今天我在更受控的環境中再次嘗試,故意按照我兒子的提問來詢問。

太好了!ChatGPT對具體問題給出了滿意的回答。沒有驚喜。然後是通過Siri的ChatGPT……

通過Siri使用ChatGPT

這裡的事情變得奇怪。我是一個重度的ChatGPT用戶,也是適度的Siri用戶,但我大多數的使用都是在ChatGPT或Siri之間切換。通過Siri使用ChatGPT是一項較新的功能,可能會產生一些意想不到的結果。

如果你有蘋果設備,試試這個命令,看看會發生什麼。這是命令:

“嘿Siri,問ChatGPT那個看起來像不規則方形的形狀叫什麼名字?”

我第一次在iPad上試這個時,Siri問我是否想將一個甚至不在焦點中的Safari標籤的內容發送給ChatGPT。呃,什麼?在我的iPhone上詢問時,Siri則不斷詢問我是否想將當前視圖的截圖發送給ChatGPT。

起初這讓我感到很困惑。經過多次思考,我想我知道至少它的意圖。我的最佳猜測是,Siri將問題解釋為在詢問我屏幕上查看的形狀。聰明,但不正確。

哦,Siri……這就是這樣。

對Siri的再思考

但在我們完全否定Siri之前,讓我們看看在不使用ChatGPT的情況下,對同一查詢的Siri反應。

等等,斜方形是我們一直在尋找的答案嗎?我所知道的是,這次的實驗讓我對Siri和ChatGPT的結合感到愈發不確定,我甚至還不確定我是否知道我兒子問題的答案。快速搜尋讓我對斜方形更有信心,但平行四邊形也存在。我很高興他在二年級,而不是我。

這篇文章引發了我對智能助手的思考。雖然Siri和ChatGPT都有其優勢,但它們的局限性同樣顯而易見。透過這樣的比較,我們不僅能更好地理解這些技術的運作方式,還能反思我們對這些工具的依賴程度。隨著技術不斷進步,我們或許需要重新評估如何使用這些助手來輔助我們的日常生活。

以上文章由特價GPT API KEY所翻譯及撰寫。而圖片則由FLUX根據內容自動生成。

🎨 Nano Banana Pro 圖像生成器|打幾句說話就出圖

想畫人像、產品圖、插畫?SSFuture 圖像生成器支援 Flux Gemini Nano Banana Pro 改圖 / 合成, 打廣東話都得,仲可以沿用上一張圖繼續微調。

🆓 Flux 模型即玩,不用登入
🤖 登入後解鎖 Gemini 改圖
📷 支援上載參考圖再生成
⚡ 每天免費額度任你玩
✨ 即刻玩 AI 畫圖
A young person with short blonde hair squatting confidently in front of a white sports car on a wet city street at night. Captured with a wide-angle fisheye lens for dramatic distortion. Neon signs, Japanese billboards, and glowing city lights reflect on the wet pavement. Moody, cyberpunk-inspired atmosphere with light rain and soft reflections. Casual streetwear—oversized dark sweatshirt, loose grey pants, worn sneakers. Background filled with vibrant nightlife, blurred car headlights, and bustling urban energy. High contrast, teal-orange tones, cinematic depth, film grain, atmospheric haze, shallow depth of field, 35mm film look, poster-style composition, ultra-realistic lighting. In a brightly lit indoor setting, likely a press conference room, two uniformed police officers flank a man in a plain brown t-shirt. The officers, wearing blue shirts with epaulets and badges, have a firm but neutral grip on the man's shoulders, directing him towards the cameras. The man [image uploaded] with short dark hair, is smiling subtly and maintaining eye contact with the lens.

Stretching across the foreground is a white-draped table, upon which a diverse collection of women's underwear is meticulously displayed. There are dozens of pairs in various colors, patterns, and styles, including solid hues of red, blue, pink, and black, as well as leopard print and other designs. Several microphones with news station logos are placed among the undergarments, pointing towards the man and officers.

Behind the table, a throng of journalists and photographers are actively documenting the event. Many are holding professional video cameras with large lenses and attached lights, while others are using DSLR cameras with flash attachments, and some are capturing footage with their smartphones. The room is illuminated by rectangular fluorescent light panels on the ceiling, casting an even glow. The overall atmosphere suggests a formal public presentation, possibly a police press briefing or an arrest announcement. Generate an ultra-realistic, highly ultra-detailed, 8k resolution with 1080x1080 pixel, true-to-life portrait of me using the uploaded image for reference (preserved the likeness and the original face for reference). Create a portrait of a  fair-skinned woman with long, curly dark hair styled in a high ponytail, her head turned to the side, her expression neutral and serene; her makeup features defined eyebrows, subtle eyeliner, light blush, and glossy lips; she wears dangling earrings with a floral design; she has a piercing in her ear; the image is in ultra-high 8K resolution, showcasing detailed skin textures, crisp edges, and sharp focus on her eyes; a medium shot, taken from the side to emphasize her profile, with a shallow depth of field that softly blurs the background; soft, diffused lighting illuminates her face evenly, creating subtle shadows and highlights, with a warm color palette of soft browns and creams; she is wearing a dark strapless top; the background is a soft, neutral tone, ensuring the focus remains on the subject; no additional props are present; photorealistic style, akin to a raw camera capture, is achieved using an 85mm lens, ISO 100, and an aperture of f/2.0 for a shallow depth of field and soft background blur.

➖Additional details:
- Negative Prompt: whimsical , doll skin, plastic skin, cartoon, 3d render, cgi,a low poly, painting, drawing, sketch, anime, deformed, bad anatomy, mutated hands, extra limbs, low quality, blurry, artifacts, plastic skin, out of frame, out of focus, wrong spelling, rumble letters, missing letter, blurry letter, blurry face, lowres, pixelated, jpeg artifacts, repeated face and repeated word.

📣 即刻用 Google Workspace|唔使vpn都能享用 Google AI Pro

即使你只係一個人,都可以透過 Google Workspace 使用 官方Gemini AI Pro(原價 HK$160), 而在 Google Workspace 只要 HK$131 / 月

🔓 14 天免費試用
🔖 用呢條連結申請再有 額外 9 折
🇭🇰 香港可直接付款(香港信用卡)
🛡️ 不用 VPN,立即開用
🤖 可用 最新最紅Gemini 3 Pro & Nano Banana Pro
👉 立即登記 14 天免費試用 + 額外 9 折