ZSI / LLMs & Programming

LLM: Large Language Model

• Trained on vast amounts of text data
• Process and predict text by identifying patterns and relationships between words and concepts

LLM & Programming

• Autocomplete
• Chat
• Agents

Vibe coding

• Building software with an LLM without reviewing the code it writes

Would AI replace programmers?

Probably not

AI and LLM programming is over-rated unless used by a senior-level software engineer in very specific and particular ways. The illusion that this will make "non-programmers" into "programmers" is a fallacy. It's fun and can do amazing things but the hype doesn't match results.

— hackerfantastic.x (@hackerfantastic) April 10, 2025

Ignore the “AGI” hype—LLMs are still fancy autocomplete. All they do is predict a sequence of tokens—but it turns out writing code is mostly about stringing tokens together in the right order, so they can be extremely useful for this provided you point them in the right direction.

If you assume that this technology will implement your project perfectly without you needing to exercise any of your own skill you’ll quickly be disappointed.

— Simon Willison: Here’s how I use LLMs to help me write code

The effect is predictable: finding work if your skill level is low becomes more difficult. However, if you are a highly skilled individual, you can eliminate much of the boilerplate work and focus on what matters. Thus, elite people are going to become even more productive.

— Daniel Lemire: How helpful is AI?

LLMs are useful

• Generate boilerplate code
• Quick prototyping
• Solving common tasks
• Generate scripts for automatization
• Explaining code

LLMs need

• Well-structured Requirements
• Context
• Human supervising

The job of a software developer is not (just) to churn out code and features. We need to create code that demonstrably works, and can be understood by other humans (and machines), and that will support continued development in the future.

— Simon Willison: Here’s how I use LLMs to help me write code

Risks

• Hallucinations
• Outsourcing understanding
• Lousing opportunity to learn

The Automation Paradox

• The more efficient the automated system, the more crucial the human contribution of the operators
  • and less prepared he is to contribute

Conclusion

• Don't let AI rob you of opportunities to learn
• Be honest
• Become professional
• Cultivate deep understanding

Think! About Your Work

Turn off the autopilot and take control. Constantly critique and appraise your work.

— The Pragmatic Programmer