Source URL: https://simonwillison.net/2025/Jun/9/david-crawshaw/#atom-everything
Source: Simon Willison’s Weblog
Title: Quoting David Crawshaw
Feedly Summary: The process of learning and experimenting with LLM-derived technology has been an exercise in humility. In general I love learning new things when the art of programming changes […] But LLMs, and more specifically Agents, affect the process of writing programs in a new and confusing way. Absolutely every fundamental assumption about how I work has to be questioned, and it ripples through all the experience I have accumulated. There are days when it feels like I would be better off if I did not know anything about programming and started from scratch. And it is still changing.
— David Crawshaw, How I program with Agents
Tags: coding-agents, ai-assisted-programming, generative-ai, ai-agents, ai, llms
AI Summary and Description: Yes
Summary: The text discusses the transformative impact of LLM-derived technology, particularly regarding programming practices. It highlights the necessity for software developers to reassess their foundational assumptions about coding in light of advancements in AI, specifically in the realm of generative AI and Agents.
Detailed Description:
The commentary from David Crawshaw emphasizes the ongoing evolution of programming methodologies due to the influence of large language models (LLMs) and AI agents. Here’s a deeper analysis of the points raised in the text:
– **LLMs and Programming**: The advent of LLMs has introduced new challenges and paradigms in programming, requiring developers to adapt to these changes.
– **Questioning Fundamentals**: The author stresses that many fundamental assumptions about programming practices are now being challenged. This can suggest a significant shift in how programmers approach problem-solving and coding.
– **Humility in Learning**: The experience of learning and adapting to these AI technologies is described as one of humility. Developers may find themselves feeling overwhelmed, as traditional knowledge may not directly translate into proficiency with LLM applications.
– **Impact on Development Process**: There is a recognition that the integration of AI agents in programming processes is not just a minor tool upgrade; it represents a fundamental shift in how software can be written and conceived.
– **Continuous Change**: The acknowledgment that this transformation is ongoing implies that professionals in the field must engage in continuous learning and adaptation.
In summary, this text serves as a reflection on the complexities and evolving dynamics within software development as influenced by AI tools, particularly generative AI. For security and compliance professionals, understanding these shifts is crucial, especially in areas related to software security and the broader implications of AI technology in development workflows. This fosters the need for updated security protocols and compliance measures tailored to the rapidly changing landscape of AI-assisted programming.