Impact of Generative AI on Software Engineering, Emerging Technology Stack, Free Course Offerings
Hi colleagues,
in this edition of the engineering ecosystem newsletter, we are switching to a curated format that features a selection of different topics. Our plan is to alternate between this format, which provides an overview of several subjects within the engineering ecosystem, and a format that focuses on a single, in-depth topic. In this curated edition, we will be covering a range of subjects:
Impact of Generative AI on Software Engineering
Generative AI is a great tool for software development, but the current expectations on the influence of generative AI on software engineering are exaggerated. Software development is a complex and creative process that involves understanding the problem domain, designing solutions, writing code, testing, debugging, deploying, ensuring qualities and maintaining software systems. Generative AI is a branch of artificial intelligence that can learn from existing data or artifacts and generate new ones that are realistic and novel. Some people may think that generative AI (e.g. ChatGPT, CoPilot and Cody) will automate software development by generating code from natural language requests or other inputs. However, this is not likely to happen in the near future for several reasons. The blog Fearing the wrong thing explores the reasons why generative AI will not replace software engineers in the near future and how it will impact the software engineering profession.
Emerging Architectures for Large Language Model Applications
The blog post Emerging Architectures for LLM Applications discusses the emerging architectures for large language models (LLMs) applications, such as natural language understanding, generation, and translation. It argues that LLMs are becoming a key component of modern software systems, and that they require new approaches to design, development, and deployment. The post identifies four main challenges for LLMs applications: data, compute, latency, and ethics. It then reviews some of the existing and emerging tools and solutions for each challenge, such as data augmentation, model compression, edge computing, and responsible AI. The post concludes by highlighting some of the open questions and opportunities for future research and innovation in LLMs applications.
The New Language Model Stack: How companies are bringing AI applications to life
The blog The New Language Model Stack: How companies are bringing AI applications to life explores the current usage of tools and the fast evolution of the stack for building applications with generative AI support.
Deep AI Learning Course Offering
If you want to get started and learn more about how to develop applications on top of generative AI, you can also check out the following external course offering.
The ChatGPT Prompt Engineering for Developers course, offered by deeplearning.ai, aims to equip developers with the knowledge and skills required to effectively utilize OpenAI's ChatGPT. The course covers essential topics such as understanding ChatGPT, designing user prompts, utilizing transformations, tokens, models, and output diversity, refining prompts into task-based templates, and overcoming biases and common pitfalls in the engagement process. This course ultimately helps developers create more versatile and accurate AI language models to address a range of use cases.
It also touches how to leverage libraries like LangChain.
https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/
There is also a course offered by Hasso Plattner Institute in German in German, which is kind of a first introduction into the topic. Suited for colleagues without a software engineering background.
Thanks and Regards,
Klaus
Subscription: If you want to get updates, you can subscribe to the free newsletter:
Mark as not spam: : When you subscribe to the newsletter please do not forget to check your spam / junk folder. Make sure to "mark as not spam" in your email client and move it to your Inbox. Add the publication's Substack email address to your contact list. All posts will be sent from this address: ecosystem4engineering@substack.com.
✉️ Subscribe to the newsletter — if you aren’t already.
Thanks for reading Software Engineering Ecosystem! Subscribe for free to receive new posts and support my work.
❤️ Share it — The engineering ecosystem newsletter lives thanks to word of mouth. Share the article with someone to whom it might be useful! By forwarding the email or sharing it on social media.