GitHub Copilot is presented as an AI pair programmer, that plugs into the user's editor. It then turns natural language prompts into code, offers multi-line function suggestions, speeds up test generation, filters out common vulnerable coding patterns, and blocks suggestions matching public code.
$10
per month
Serenade.ai
Score 10.0 out of 10
N/A
Serenade.ai is an AI code generation tool that offers code with voice functionality, enabling users to write code using natural speech. Serenade's speech-to-code engine is designed for developers from the ground up and fully open-source.
Copilit is fantastic at the following: 1. Solving simple, well-defined problems, such as implementing an algorithm, manipulating a data structure, or string manipulation and regex. 2. Implementing simple APIs that are mainly CRUD in nature, with moderate business logic inside them, which may involve some processing or passing the data through an algorithm. 3. Implementation of well-defined activities, such as implementing a connection to an Oracle DB using Hibernate or JDBC, or implementing boilerplate code for a backend service to listen to Kafka events. It is not that great when it comes to understanding and implementing code in a proprietary DSL. It struggles when implementing a major feature across a complex codebase. I believe developers should also adopt the trust-but-verify paradigm when expecting highly secure or regulated code from GitHub Copilot.
I've met several engineers who have temporarily lost their ability to use the mouse / keyboard. But its more than an accessibility tool. Being able to simply say "Refactor this method to iterate over the collection as a collection of promises and await all promises after the iteration."... and then get that done, was amazing.
The voice recognition takes some getting used to. Just like using a new keyboard, you get used to what you need to over-enunciate or be really clear on. Being able to train the model / interpreter they are using on my voice, tonation, dictation, accent, etc would be a major benefit.
Having to have a clear picture in your head about the code you want to write is a mental challenge. But this is more of a challenge of the process than the application. I found littering the code I wanted to refactor with #todo comments and then asking Serenade.ai to implement the series of comments to be the best method of planning and then implementing the code.
I feel that GitHub Copilot's overall usability is good due to its tight integration with Visual Studio and the workspace. However, developers expect greater ease of use, as there is a learning curve to realize productivity gains with the tool fully. I think there is room for improvement in GitHub Copilot's UI integration within Visual Studio.
It is useful that copilot integrates so well with vscode, which is a very common IDE. I used Tabnine for a little while but it was not that intuitive, and did not seem as helpful as GitHub copilot was. I have enjoyed GitHub copilot a lot, especially the ease of hitting the tab key and seeing quick progress in my tasks.
Until very recently, there was nothing on the market which allowed you to code with voice with the accuracy that Serenade.ai provided. Even now there is nothing that I'm aware of that allows you to interface with your ENTIRE PC/Mac with your voice.
I was able to continue my engineering position, earning salary, without taking disability until after my surgery. During that time I was able to continue to participate.
