With the growing discussions about the integration of artificial intelligence (AI) into software development via tools like ChatGPT and Github Copilot, author has explored these AI-driven coding aids for some time. Initially, he engaged with Tabnine, a tool similar in function to Github Copilot, albeit a paid service, and his initial experiences were less than satisfactory. Subsequently, author approached AI-based products from other companies with a certain degree of skepticism. By Michał Szulczewski.
Tha article focuses on:
- Advance chat bots – ChatGPT and Github Pilot
- Potential challenges encountered by developers in the utilization of AI chatbots
- Suboptimal recommendations for less common libraries and unconventional use cases
- Reviewing new iterations of code imposes considerable cognitive load
- Mismatched Variable and Function Nomenclature
- Code often does not function
- Textual chat flow differs from programming flow
- Positive aspects of using AI chatbots
- Facilitating exploration in unfamiliar domains
- Employing chatbots as an interactive rubber duck
- Streamlining the configuration of fundamental structures
- Operations on selected code
- Extensions for Integrated Development Environments (IDEs)
- AI vs. LSP
… and more. In author’s view: “Drawing from my experience of over eight years as a programmer, I’ve come to appreciate that programming is an ongoing journey of acquiring new knowledge and leveraging emerging libraries. However, given the magnitude and diverse nature of errors that AI can introduce, along with the ever-evolving landscape of programming languages and libraries, AI may never fully replace human programmers.” Interesting read!
[Read More]