Use iPhone shortcuts actions “Use On-Device Model”, “Summarize” and request to Gemini free account to summarize the highlighted text from When AI writes almost all code, what happens to software engineering?
Looks to me, On-Device AI model is good enough.
Prompt
Use the same prompt for On-Device model and Gemini
Summarize the input provided as Shortcut Input. The summary must be shorter than 200 words and formatted in a markdown code block. Ensure that all section titles within the summary are rendered as Level 2 Markdown Headings (starting with ##), not as simple bullet points or numbered lists.
On-Device model
The Rise of AI in Software Engineering
The article explores the transformative impact of AI on software engineering, particularly with the advent of AI-powered coding tools like Claude Code. The author shares their experience building production software on their phone using Claude Code, highlighting the significant changes in the field.
Key Points
- Declining Value of Expertise: The expertise of programmers, language polyglots, and specialists in specific stacks may become less valuable as AI can generate code efficiently.
- Emergence of Tech Lead Traits: Being more product-minded and having strong leadership skills will be in higher demand.
- Overlap between Product Managers and Software Engineers: The roles of both professionals are expected to overlap more than ever before.
- AI-Generated Code: AI models like Opus 4.5, GPT-5.2, and Gemini 3 have demonstrated their ability to generate code, making it possible for developers to focus on higher-level tasks.
- Future of Software Engineering: The profession is being refactored, and developers need to adapt to a new world where AI plays a significant role in code generation and software development.
Gemini free
Summary of AI’s Impact on Software Engineering
The Tipping Point and New Paradigm
- Recent AI model releases (Opus 4.5, GPT-5.2, Gemini 3) are the 【tipping point】, enabling AI to generate nearly all code.
- Engineers can now build production software from mobile devices, like using Claude Code to create and merge PRs.
- The cost of software production is 【trending towards zero】, with AI behaving like a senior engineer.
Evolving Roles and Skills
- 【Declining value of expertise】 in prototyping, polyglotism, or stack specialization.
- Increased demand for 【product-minded tech leads】.
- Software engineers must master new 【programmable abstraction layers】 involving agents, prompts, and tools.
- Product managers and engineers will 【overlap more】.
Future Implications
- Expectation for all developers to 【generate concept apps fast】.
- AI will handle 90%+ of code generation and refactoring.
- Engineers are ceasing to write code by hand, prioritizing 【leveraging AI for productivity】.
- A need to continually 【re-adjust expectations】 as AI capabilities advance.
Summarize action
Use shortcuts action “Summarizize”
AI coding tools are becoming so advanced that they can generate most of the code for many developers, significantly impacting the software engineering profession. This shift is leading to a decline in the value of traditional expertise like prototyping and language proficiency, while increasing the demand for tech leads with product-minded skills. As AI takes over coding tasks, software engineers must adapt to a new programmable layer of abstraction and leverage AI tools to remain competitive.