ChatGPT continues to attract attention. Imaginative use cases and innovative approaches to prompting mean it's gaining expanding utility over time. GPT4, the large language model (LLM) that powers ChatGPT, now also has the ability to integrate with external tools such as a knowledge management repository, sandboxed coding environment or web search. The recent introduction of ChatGPT Enterprise may help ease intellectual property concerns, while providing "enterprise" features such as usage tracking and better user management through SSO.
Although ChatGPT's ability to "write" code has been much vaunted, we think organizations should be looking at using it across the full software lifecycle to improve efficiency and reduce errors. For example, ChatGPT can provide additional perspectives or suggestions for tasks as diverse as requirements analysis, architectural design or the reverse engineering of legacy systems. We still think ChatGPT is best used as an input to a process — such as helping with a first draft of a story or the boilerplate for a coding task — rather than a tool that produces "fully baked" results. That said, its capabilities are improving each week, and some programming tasks may now be fully possible by careful prompting, which is an art in itself.
ChatGPT is an interesting tool that has the potential to be useful for various aspects of the software creation process. As a large language model (LLM) that has "read" billions of web pages, ChatGPT can provide additional perspectives and assist with different tasks, from generating ideas and requirements to creating code and tests. Its ability to work across multiple parts of the software lifecycle makes it a versatile tool that might improve efficiency and reduce errors in the development process. GPT4, the LLM that powers ChatGPT, now also has the ability to integrate with external tools such as a knowledge management repository, sandboxed coding environment or web search. For now, we think that ChatGPT is best used as an input to a process, such as helping with a first draft of a story or the boilerplate for a coding task, rather than a tool that produces "fully baked" results.
There are concerns around intellectual property and data privacy with these AI tools, including some unresolved legal questions, so we recommend organizations seek advice from their legal teams before use. Some of our clients have already begun experimenting with ChatGPT across various stages of the software lifecycle, and we encourage others to explore the tool and assess its potential benefits. We expect that, like GitHub Copilot, a "for business" offering will soon be available which may ease intellectual property concerns.