返回资讯中心
外部精选
软件工程
#开发者实时流

Revision Prompting: Diff your inputs for consistency and efficiency

Industrial prompting typically processes some Input data with an Instruction to produce some Output.

Hacker News 最新idiliv2026/11/1 · 16 天前3 分钟阅读

以下正文同步自 Hacker News 最新,版权归原站所有,已转换为易读排版。

Industrial prompting typically processes some Input data with an Instruction to produce some Output. Whenever the Input gets updated, industrial prompting naively re-runs the Instruction on the UpdatedInput to produce the UpdatedOutput. This approach has two downsides:

Revision prompting resolves both downsides of naive re-runs by operating on the input and output revisions instead of the full input and output.

Assume you have processed some Input with an Instruction to produce some Output by prompting an LLM with

Now, Input has been updated, and you also want to process the UpdatedInput. Revision Prompting processes the UpdatedInput by constructing the RevisionPrompt as

The input got updated as follows: diff(Input, UpdatedInput).

Please produce a patch to update the output.

The LLM responds to the RevisionPrompt with the OutputPatch that we apply to the Output to obtain the UpdatedOutput.

You translate the product page of an e-bike to German with the prompt

Later, a battery upgrade increases the range from 80 km to 100 km. Instead of re-translating the whole page, you prompt

Applying the OutputPatch to the original Output produces the updated translation.

The OutputPatch contains only two lines of text instead of a full re-translation. Unchanged content stays consistent with the original translation.

正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。

打开原文
去社区讨论 →