New GPT-3, Now Edit and Insert Content into Existing Text

GPT-3 and Codex can now edit text, changing what's currently there or adding text to the middle of content

OpenAI has released new versions of GPT-3 and Codex which can edit or insert content into existing text, rather than just completing existing text. These new capabilities make it practical to use the OpenAI API to revise existing content, such as rewriting a paragraph of text or refactoring code. This unlocks new use cases and improves existing ones.

GPT-3 and Codex have traditionally added text to the end of existing content, based on the text that came before. Whether working with text or code, writing is more than just appending; it's an iterative process where existing text is revised. GPT-3 and Codex can now edit text, changing what's currently there or adding text to the middle of content. 

Inserting Into the Middle of Text

The new insert capability adds the contextually relevant text in the middle of existing content. Providing future context to the model can improve the quality of completions for applications such as writing long-form text, transitioning between paragraphs, following an outline, or guiding the model toward an ending.

Editing Existing Text

A meaningful part of writing text and code is spent editing existing content. OpenAI has released a new endpoint in beta called edits that changes existing text via an instruction, instead of completing it.

Editing works by specifying existing text as a prompt and instruction on how to modify it. The edits endpoint can be used to change the tone or structure of the text, or make targeted changes like fixing spelling. It has also observed edits to work well on empty prompts, thus enabling text generation similar to the completion's endpoint. 

The edits endpoint is particularly useful for writing code. It works well for tasks like refactoring, adding documentation, translating between programming languages, and changing coding style.