蘋果新AI模型表現遜色惹熱議




蘋果升級版AI模型表現令人失望

蘋果公司近日宣布更新其AI模型,以驅動其在iOS、macOS等多個平台上的Apple Intelligence功能。然而,根據該公司自身的基準測試,這些模型在性能上卻落後於競爭對手的舊款模型。

蘋果在周一的一篇部落格文章中表示,人類測試者對該公司最新「Apple On-Device」模型生成的文本質量進行了評估,該模型可以在iPhone等設備上離線運行。測試結果顯示,其生成的文本質量與谷歌和阿里巴巴的同類模型相似,但並未超越它們。而對於更強大的「Apple Server」模型,測試者則認為它落後於OpenAI去年的GPT-4o模型。

在另一項評估蘋果模型圖像分析能力的測試中,人類評分者更傾向於Meta的Llama 4 Scout模型,而不是Apple Server。值得注意的是,Llama 4 Scout在多項測試中的表現其實落後於谷歌、Anthropic和OpenAI等AI實驗室的領先模型。

這些基準測試結果支持此前關於蘋果AI研究部門難以趕上競爭對手的報導。近年來,蘋果的AI能力一直令人失望,一項承諾的Siri升級也已被無限期推遲。一些客戶甚至起訴蘋果,指控該公司宣傳了尚未交付的AI功能。

除了生成文本外,「Apple On-Device」模型(參數約30億)還驅動了摘要和文本分析等功能。該模型現已向第三方開發者開放,開發者可以透過蘋果的Foundation Models框架訪問它。

蘋果表示,「Apple On-Device」和「Apple Server」都具有比前代模型更好的工具使用和效率,並且可以理解約15種語言。這得益於其擴大的訓練數據集,包括圖像數據、PDF、文檔、手稿、資訊圖表、表格和圖表。

作為編輯,我認為蘋果在AI領域的表現令人失望,這可能與其在AI研究方面的投入和人才流失有關。蘋果需要加強在AI領域的研發和創新,才能與競爭對手如OpenAI、谷歌和Meta等公司競爭。同時,蘋果也需要加強與開發者的合作,推動AI技術在實際應用中的落地。

此外,蘋果的AI模型在圖像分析能力方面落後於競爭對手,這可能與其在計算機視覺領域的技術積累有關。蘋果需要加強在計算機視覺領域的研究和創新,才能提高其AI模型的圖像分析能力。

總的來說,蘋果在AI領域的表現令人失望,但這也為蘋果提供了改進和創新的機會。蘋果需要加強在AI領域的研發和創新,才能與競爭對手競爭並推動AI技術在實際應用中的落地。

🎨 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
Certainly! Here is your enhanced, artistic, and detailed prompt for an AI image generator:

---

A captivating portrait of a young Asian woman, inspired by Imada Mio and embodying an exquisitely delicate, doll-like (精緻洋娃娃臉) aesthetic. She has large, round, expressive eyes that radiate innocence and curiosity, subtly accented with a moist shimmer. Her petite V-line face is framed by soft, rosy cheeks, and her lips are naturally pink and slightly parted, exuding an energetic, slightly flirty, yet pure aura. Her expression is a candid blend of sweetness and playful allure.

Her long, dark brown hair is artfully tousled with a messy morning (剛睡醒的凌亂感) effect—loose strands fall gently around her face, conveying natural volume and effortless beauty. The hair has a silky texture, catching the light in places, suggesting a recent awakening.

She is dressed in an oversized, translucent white button-down shirt (男友風白襯衫) with the top buttons casually undone, delicately revealing her collarbones and a slender neckline. The shirt drapes loosely, giving a tasteful "bottomless" look (下衣失蹤風格), her bare legs just barely visible beneath the shirt's hem, enhancing the innocent-meets-sensual ambiance.

The composition is styled in the manner of a Japanese Gravure Photobook (寫真集風格), exuding a pure & sexy vibe with an airy, dreamy atmosphere. Employ bright, high-key lighting for a clean, luminous effect that highlights her velvety soft skin texture. Use Fujifilm PRO 400H film tones for subtle pastel hues, gentle contrast, and a seamless blend of natural colors, further enriching the soft, ethereal, and intimate photographic quality.

The background is minimalist and softly blurred, ensuring complete focus on the subject, and enhancing the overall sense of warmth, comfort, and inviting allure typical of high-end Japanese photobooks.

--- Google Gemini / Meta AI 🎯💯 

Promte ✅ 

A hyper-realistic night portrait of a handsome young man leaning casually against a black luxury car, laughing heartily with head tilted slightly back. He has a groomed beard, short styled dark hair, and is wearing a plain black long-sleeve crewneck sweatshirt. The lighting is low-key and cinematic, with the subject's face warmly illuminated against the darkness. The background features a dark street with beautiful, creamy golden bokeh orbs from distant streetlights and car headlights. Shot on a Sony A7R IV with an 85mm f/1.4 lens, shallow depth of field, sharp focus on the smile, high contrast, moody urban night atmosphere, 8k resolution. Size 4:5 ratio 100% use my upload reference image Create a very realistic, cinematic image of a woman, with 100% of her original facial features maintained from the provided image. Do not alter the face, focusing on realistic details of the facial structure, eyes, eyebrows, nose, mouth, and expression. The lower left corner of the image features the Facebook logo and the text Nomahtan Kung.
Makeup: sharp Asian-style eyebrows, sharp Cat Eye eyeliner, and gradient red lipstick
​Her lips are parted slightly, revealing a hint of teeth, and are coated in a glossy, natural-toned red lipstick that catches the light, giving them a luscious appearance. The subtle lines and contours of her philtrum and cupid's bow are visible. with the subtle texture of skin visible. Wears a necklace with the text Kunika and other small matching accessories, such as earrings or a wrist bracelet.