使用 AI：代碼轉換

不久前，LLM（大型語言模型）還不可能重寫程式碼。每個法學碩士都有一個令牌限制，它確定了它可以吸收和應用的字數。由於令牌限制較低，模型無法吸收執行程式碼轉換等複雜任務所需的資訊量。

Software development company Mantle recently faced a common challenge: they had built a next-generation equity management platform prototype in a specific coding language that was perfect for speedy interaction in response to feedback from customers.

軟體開發公司Mantle最近面臨著一個共同的挑戰：他們用特定的編碼語言建立了下一代股權管理平台原型，該原型非常適合快速互動以回應客戶的回饋。

However, the code used in their production tech stack was different, and to ship the product, Mantle would need to convert the codebase from one language to another. This is a notoriously onerous task that is regularly faced by software teams and enterprises.

然而，他們的生產技術堆疊中使用的程式碼不同，為了交付產品，Mantle 需要將程式碼庫從一種語言轉換為另一種語言。這是軟體團隊和企業經常面臨的一項極為繁重的任務。

“The effort is justified, but the process is painful,” said Dwayne Forde, Mantle co-founder and CTO. “Instead of moving a customer-facing roadmap forward, you are now going to spend a significant portion of valuable engineering time recreating existing functionality.”

Mantle 聯合創始人兼首席技術長 Dwayne Forde 表示：“這種努力是合理的，但過程很痛苦。” “您現在將花費大量寶貴的工程時間來重新創建現有功能，而不是向前推進面向客戶的路線圖。”

Wondering if AI could help, Forde—a trusted industry leader with more than 20 years of engineering experience in roles with companies including VMware and Xtreme Labs—chronicled the process recently in a blog post on Mantle called “Working with AI: Code Conversion.”

Forde 想知道AI 是否可以提供幫助，Forde 是一位值得信賴的行業領導者，在VMware 和Xtreme Labs 等公司擁有20 多年的工程經驗，最近在Mantle 上發表的一篇名為“使用AI：代碼轉換」的部落格文章中記錄了這一過程。

He hopes the case study will serve as a useful resource to other tech teams, helping them save time and effort.

他希望這個案例研究能成為其他技術團隊的有用資源，幫助他們節省時間和精力。

It is the second in a series of instructional guides Forde has written for technical teams, as part of an effort to advance the collective interests of the sector by showing how AI can accelerate and enhance their work.

這是福特為技術團隊編寫的一系列指導指南中的第二份，作為透過展示人工智慧如何加速和增強他們的工作來促進該行業集體利益的努力的一部分。

“Our goal wasn’t to achieve 100% perfectly crafted code,” Forde noted. “The goal was to get 80% of the boilerplate and repeated patterns out of the way so that engineers could focus on high-value validation and verification and we could ship the product.”

「我們的目標不是實現 100% 完美編寫的程式碼，」Forde 指出。 “我們的目標是消除 80% 的樣板文件和重複模式，以便工程師可以專注於高價值的驗證和驗證，並且我們可以交付產品。”

Not too long ago, it wasn’t possible for LLMs (Large Language Models) to rewrite code. Each LLM has a token limit, which establishes how many words it can absorb and apply. With lower token limits, the models are unable to absorb the amount of information required to perform complex tasks like code conversions.

不久前，LLM（大型語言模型）還不可能重寫程式碼。每個法學碩士都有一個令牌限制，它確定了它可以吸收和應用的字數。由於令牌限制較低，模型無法吸收執行程式碼轉換等複雜任務所需的資訊量。

But with rapid advancements in LLM software came higher token limits, and Forde realized his team had exciting new options in front of them. Higher limits meant that models could increase their reasoning, perform more complex math and inference, and input and output context in dramatically larger sizes.

但隨著 LLM 軟體的快速進步，代幣限制也隨之提高，Forde 意識到他的團隊面前有令人興奮的新選擇。更高的限制意味著模型可以增強推理能力，執行更複雜的數學和推理，並以更大的尺寸輸入和輸出上下文。

One million tokens means, according to Medium, that a model can do the equivalent of reading 20 novels or 1000 legal case briefs.

根據 Medium 的說法，100 萬個代幣意味著一個模型相當於閱讀 20 本小說或 1000 個法律案件摘要。

Forde and his team understood that this dramatically larger token limit would allow them to feed entire coding languages into an LLM, essentially teaching it to be bilingual.

福特和他的團隊明白，這種極大的令牌限制將使他們能夠將整個編碼語言輸入到法學碩士中，本質上是教它雙語。

Because converting code is extremely labour-intensive, Mantle knew that having an LLM convert even small amounts of code from one language to another would be hugely beneficial to the delivery time of the engineering project.

由於轉換代碼是極其耗費人力的工作，Mantle 知道，讓法學碩士將少量代碼從一種語言轉換為另一種語言，將極大縮短工程項目的交付時間。

“We developed an approach that reduced the scope of work by two-thirds and saved months of developer time,” Forde wrote in his post.

「我們開發了一種方法，將工作範圍縮小了三分之二，並節省了開發人員數月的時間，」福特在他的貼文中寫道。

Converting the Mantle prototype project into a new code language would have normally taken months of manual labour.

將 Mantle 原型專案轉換為新的程式碼語言通常需要數月的體力勞動。

Instead, Forde said his engineers focused their time experimenting with how to best prompt an LLM to do much of the work for them.

相反，福特表示，他的工程師將時間集中在試驗如何最好地促使法學碩士為他們完成大部分工作。

It wasn’t just as simple as feeding the code languages into the LLM and asking it to translate.

這不僅僅是將程式碼語言輸入 LLM 並要求其翻譯那麼簡單。

Under Forde’s watch, the Mantle team went through a process of innovation and discovery to figure out the best instructions, context and guidance to provide the LLM in its work.

在 Forde 的監督下，Mantle 團隊經歷了一個創新和發現的過程，以找出在其工作中提供法學碩士的最佳說明、背景和指導。

They fed the model code snippets from their prototype source language, as well as existing production code patterns, descriptions of their target architecture, and provided the LLM with context about specific libraries and utilities used in Mantle’s own tech stack.

他們從原型原始語言以及現有的生產程式碼模式、目標架構的描述中提供模型程式碼片段，並向法學碩士提供有關 Mantle 自己的技術堆疊中使用的特定程式庫和實用程式的上下文。

“We have certain libraries that we prefer, so adding a section of context was very helpful to make sure the LLM output code was compatible with what we use,” said Forde.

「我們有某些我們喜歡的程式庫，因此添加上下文部分對於確保 LLM 輸出程式碼與我們使用的程式碼相容非常有幫助，」Forde 說。

The team even fed the LLM screenshots to demonstrate how they wanted the information to be presented, something that would not be obvious to AI from the code language alone.

該團隊甚至提供了法學碩士螢幕截圖來演示他們希望如何呈現訊息，而僅從代碼語言來看，這對於人工智能來說並不明顯。

“Screenshots of the existing application give the LLM a visual layout of the application,” said Forde. “The context and direction you provide don’t have to be all verbal. You can use visual reference points as well to get the output you’re after.”

「現有應用程式的螢幕截圖為法學碩士提供了應用程式的可視化佈局，」福特說。 「你提供的背景和方向不必都是口頭的。您也可以使用視覺參考點來獲得您想要的輸出。

In his blog post, Forde breaks down the step-by-step process Mantle used to convert their code. The process is innovative, iterative and – at times – playful.

在他的部落格文章中，Forde 詳細介紹了 Mantle 用於轉換程式碼的逐步過程。這個過程是創新的、迭代的，有時還很有趣。

At one point, the Mantle team instructed the LLM to “act like a software engineer who could only answer in source code.”

Mantle 團隊一度指示法學碩士「像個只能用原始碼回答的軟體工程師一樣」。

The Mantle team asked the LLM to convert only small sections of code at a time, checked its work, corrected any misinterpretations, and then moved on.

Mantle 團隊要求法學碩士一次只轉換一小部分程式碼，檢查其工作，糾正任何誤解，然後繼續前進。

The step-by-step experimentation allowed the Mantle team to refine and improve its work over time, and create an effective process that can now be replicated in future projects.

逐步的實驗使 Mantle 團隊能夠隨著時間的推移完善和改進其工作，並創建一個可以在未來專案中複製的有效流程。

“Once the file was generated, our team either reviewed and adjusted the output manually or adjusted the

「文件生成後，我們的團隊要么手動審查並調整輸出，要么調整