GitHub Copilot vs. Perplexity

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.

Incentivized

Perplexity is helpful when you want auto-code generation for day-to-day problem scenarios such as Powershell script to accomplish a task, Code to invoke a REST API, Class generation from JSON/XML data, etc. It is also helpful when you want to correct or optimize code that you have self-written. Perplexity might not be best suited for scenarios when you need 100% accuracy without your self-verification of correctness.

Incentivized

• Make code development faster and quicker.
• Helps write better code standards for projects.
• Provide the latest functions from the technology.
• Notifies about the deprecated functions.

Incentivized

• Research the company that my prospects work for.
• Research background on my prospects.
• Combine those two and come up with about one page on how to approach them based on the space (persona) I created.

Incentivized

• The only issue I faced is the context token size, it can be increase.
• Sometime with agent mode it takes too much time, which can be reduced but I understand it also depends on the complexity of the given task.

Incentivized

• Image generation is not upto mark
• Data analysis for excel is way off
• Getting insights on data not available online is hard
• Need to embed like copilot in assisting day to day activities

Incentivized

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.

Incentivized

It's great, but doesn't necessarily feel like it adds enough value over using CoPilot, ChatGPT, or whichever generative AI tool your business already uses. Time will tell if this model continues to be developed, and whether it remains competitive with the other big models out in the industry, and innovating features and integrating more use cases fast.

Incentivized

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.

Incentivized

I use all three at present, Perplexity IS outstanding when It comes to researching, like a search engine on steroids. If you need programming skills Claude or Chatgpt seem better suited for the task. What I normally do in a project IS use all three in order to arrive at a more insightful outcome. The BEST of all world.

• Our ROI of the purchase of Copilot was met in less than a day. The timesave cannot be overstated
• Programmer boredom/dissatisfaction is down because of less repetetive crud work.

Incentivized

• Increases efficiency
• Saves costs (e.g. for creation of creative content)
• Frees up time that can be used for other productive actions

Incentivized