計算機工程
我是一位長期從事計算機工作的工程師, 我主要是進行多種金融軟件的開發, 也開發了一些其他領域的軟件.
隨著DeepSeek的出現，有關其是否在開發過程中抄襲了ChatGPT的技術的討論逐漸增多。本文將基於對比實驗，探討DeepSeek是否借用ChatGPT的技術，並揭示其在技術實現方麵可能存在的相似性和差異性。
一、驗證DeepSeek的思路
一般來說，驗證兩個係統是否相同，最直接的方法是比較它們在相同輸入條件下的輸出結果。如果兩個係統在處理同一問題時給出的答案完全一致，則可以推測這兩個係統在算法或架構上存在高度的相似性，甚至可能是相同的。在本研究中，主要采用以下兩種驗證方法：
- 信息一致性檢驗
首先，通過從兩個不同的數據庫中調取相同的信息，觀察其輸出結果。如果兩個數據庫返回的結果完全一致，那麽這兩個數據庫的底層結構很可能是相同的。 - 特殊變量【MASK】的使用
利用特殊的變量【MASK】獲得可能性詞匯，檢驗兩種算法是否等同. 具體來說，[MASK] 是一個占位符，表示在這個位置需要填充一個詞語。模型會根據句子中的其他詞語（即上下文）推理算法，預測最合適的詞語，並將其替換到 [MASK] 的位置。通過比較DeepSeek與ChatGPT在相同輸入下對【MASK】位置的填充結果，檢驗兩者的推理機製是否一致。
隨機抽取了67個檢測樣本進行對照檢驗， 發現DeepSeek與ChatGPT具有高度的相似性。下麵舉具體驗證例子實例和結果.
實例1
輸入句子：
Up to 30 [MASK] and babies died at Furness General Hospital because of failings by staff and management, a damning report is [MASK] to reveal.
ChatGPT輸出：
Up to 30 mothers and babies died at Furness General Hospital because of failings by staff and management, a damning report is expected to reveal.
DeepSeek輸出：
Up to 30 mothers and babies died at Furness General Hospital because of failings by staff and management, a damning report is expected to reveal.
在這個示例中，DeepSeek和ChatGPT在預測【MASK】位置時，給出填充“mothers”和“expected”結果完全一致。
實例2
輸入句子：
Taking in the sights of [MASK] is nothing short of [MASK], with its famous souk which houses over 60,000 stalls full of colorful handmade wares.
ChatGPT輸出：
Taking in the sights of Marrakech is nothing short of breathtaking, with its famous souk which houses over 60,000 stalls full of colorful handmade wares.
DeepSeek輸出：
Taking in the sights of Marrakech is nothing short of breathtaking, with its famous souk which houses over 60,000 stalls full of colorful handmade wares.
在這個例子中，DeepSeek和ChatGPT也給出了完全相同的預測詞匯“breathtaking”和“Marrakech”，驗證了兩者在推理和預測時的一致性。
實例3
輸入句子：
Ultimately, the goal of life is a [MASK] that each individual must define for themselves based on their own beliefs, values, and experiences.
ChatGPT輸出：
Ultimately, the goal of life is a journey that each individual must define for themselves based on their own beliefs, values, and experiences.
DeepSeek輸出：
Ultimately, the goal of life is a journey that each individual must define for themselves based on their own beliefs, values, and experiences.
在這個實例中，“journey”這一填充詞在DeepSeek和ChatGPT的輸出中完全一致.
實例4和實例5是把由不同部分組成的大段訊息進行比較, 任何微小部分的不同, 都可以導致信息的差異性產生. 同時如果算法不同, 也可以導致結果不同. 但是如果信息完全一致且算法也一致的情況下, 結果應是等同的.
實例4
輸入句子：
I purchased the variety pack of Martinsons and the Brown Gold they are both from the same vendor. I did not like the taste of the Martinson product at all. I threw it away, not the product I expected at all. The Brown Gold was more palatable, however certain flavors with this brand also feel short in particular the Costa Rican named product was extremely too bitter. I would agree with most that this does give you a lower cost per serving, but when the coffee is inferior and the taste match is also, I think the best descriptor is [MASK].
ChatGPT輸出：
cheap
DeepSeek輸出：
cheap
這個例子展示了兩者都將【MASK】位置填充為“cheap”，進一步證明它們在算法和推理機製上是相同的。
實例5
輸入句子：
Not bad. "These are small and very salty. The taste is good, but very strong, so it's a good thing the package contains a small amount. It only takes a few little crisps to cure my salty/crunchy craving. I can snack on one package for an entire day. Of course, these would not be a good snack if you're very hungry, because there isn't enough there to fill you up. For less than $1 per pack, it's an [MASK].
ChatGPT輸出：
"For less than $1 per pack, it's an okay deal."
DeepSeek輸出：
"For less than $1 per pack, it's an okay deal."
在這個示例中，DeepSeek和ChatGPT在預測【MASK】位置時，給出填充“For less than $1 per pack, it's an okay deal.”結果完全一致。
從上述的對比實驗和技術分析可以得出結論，在使用【MASK】變量的測試中，DeepSeek和ChatGPT在所有樣本中的輸出結果完全一致，表明它們采用了相同的推理算法, 技術框架和數據源。由於DeepSeek與ChatGPT之間高度的相似性，DeepSeek的技術可能涉嫌抄襲。
