Choose Boring Technology and LLMs
The author favors reliable technologies like relational databases and programming languages while embracing accessible large language models, sharing resources for learning and inviting connections as a software consultant.
Read original articleThe article discusses the author's preference for "boring" technology, such as relational databases and established programming languages, while also embracing the rapid advancements in large language models (LLMs). The author highlights the accessibility of LLMs, allowing anyone to engage in prompt engineering and develop digital products. They emphasize their approach of focusing on simple, reliable technologies like Go and SQLite, while selectively using cloud services for specific needs. The author expresses excitement about learning to integrate LLMs into applications, covering topics like prompt engineering and multi-modality. They also share resources for further learning, including writings by Simon Willison, a new book on prompt engineering, and free video courses on LLMs and neural networks. The author identifies as a professional software consultant and developer, inviting readers to connect through various platforms.
- The author prefers established, reliable technologies over complex, trendy software.
- LLMs are seen as accessible tools for anyone interested in prompt engineering.
- The author focuses on integrating LLMs into applications while using simple technologies.
- Resources for learning about LLMs and prompt engineering are provided.
- The author identifies as a professional software consultant and developer.
Related
I worry overall that this could signal the complete end of new programming languages except in a few special cases. (Which I think was already a worrying trend before AI- see Bret Victor’s “The Future of Programming” talk).
Which is same point that the original post "choose boring technology" makes. I don't see the contradiction.
On the other hand, this could be the same slippery slope that starts at "choose a boring project because it has mature tooling" but ends at "IDE's are a language smell". If the language is so boring that you can't focus on it without an LLM doing the menial work, that could be because there is too much menial work to start with.
Did anyone try working with LLMs and Swift for example? Is the AI suggesting deprecated libraries from earlier iOS versions / generally having trouble? Or is it working fine?
Choose boring technology aka pick the technologies I think are the best.