news

on thursday, october 3rd, eastern time, openai updated chatgpt with new additionsfunction——Canvas。

it is reported that canvas is developed based on the gpt-4o model, which provides a separate window.you can perform programming and writing tasks with chatgpt, and will help you provide opinions, review and perform specific functions.

for example, when you encounter difficulties while writing code, canvas can highlight problematic code segments and help chatgpt provide inline debugging suggestions to quickly fix these errors.

to put it simply, canvas can be regarded as a built-inAI Agentthe function is to use ai to guide and assist chatgpt to perform tasks together, so that the output content quality is better and more accurate.

openai said that canvas introduces a new way of collaboration - not just through dialogue, but through users and ai working side by side to create and improve ideas. with the help of canvas, chatgpt can better understand the context of the task to be completed by the user. users can highlight specific sections to indicate exactly what they want chatgpt to focus on. just like a copy editor or code reviewer, it can provide inline feedback and suggestions with the entire project in mind.

in terms of writing, some shortcuts provided by canvas include:

suggested editors: chatgpt provides inline suggestions and feedback.

adjust length: edit the document length, shorten or lengthen it.

change the reading level: adjust the reading level to meet the needs of people with multiple reading abilities from kindergarten to postgraduate level.

add final touches: check for grammar, clarity, and consistency.

add emoticons: add relevant emojis for emphasis and color.

openai introduced how to write code in the canvas interface, saying that coding is an iterative process and tracking all revisions of the code in chat can be difficult, while canvas makes it easier for users to track and understand changes to chatgpt. openai plans to continue to increase the transparency of such edits.

encoding shortcuts include:

review code: chatgpt provides inline suggestions for improving users' code.

add logging: insert statements to help users debug and understand the code.

add comments: add comments to the code to make it easier to understand.

fix errors: detect and rewrite problematic code to resolve errors.

port to language: translate user's code into javascript, typescript, python, java, c++ or php.

for coding, levine demonstrated asking chatgpt to create an api web server in python. the server code is generated in the canvas window. press the "add comment" button and chatgpt will add inline documentation explaining the code in plain english. users can highlight a piece of code created by chatgpt and have it explain it or ask questions about it. chatgpt also has a "review code" button, which will suggest specific edits to the code in the window, whether generated by gpt or written by the user themselves, and allow the user to approve, edit themselves, or reject the suggestion. if the user presses approve, chatgpt will try to fix the error itself.

according to test data released by openai, canvas has demonstrated its strong capabilities in triggering decision-making performance, especially in writing and coding tasks. it can determine when the canvas function should be triggered with a high accuracy, with an accuracy of 83% for writing tasks and 94% for coding tasks.

in terms of editing behavior, canvas also performs well.the performance of targeted editing is improved by 18% compared to the baseline model, showing significant performance improvements. canvas' model can intelligently decide whether to perform targeted editing or complete rewriting based on user operations on the interface. this ability to make intelligent editing decisions based on user interaction is a major advantage of canvas.

in addition, canvas has achieved remarkable results in generating reviews. through manual evaluation,canvas outperforms baseline models by 30% in accuracy and 16% in quality. although there are certain difficulties in automated evaluation, the results of manual evaluation demonstrate the performance improvement of canvas in review generation.

daily economic news comprehensive self-public information

daily economic news