@MaximeRivest: Too may software engineers look down on vibe coding, this chart is good at showing when to use which. We have jagged ex…
Summary
A commentary on how software engineers should recognize when they are engaging in 'vibe coding' (AI-assisted coding) and that there is jagged expertise, similar to models, in development practices.
View Cached Full Text
Cached at: 07/14/26, 04:29 PM
Too may software engineers look down on vibe coding, this chart is good at showing when to use which.
We have jagged expertise, just like model have jagged intelligence, we most also recognise that, sometimes, we are in the vibe coding territory even if we didn’t mean to be. https://t.co/25hVCk2xO8
Similar Articles
Vibe coding and agentic engineering are getting closer than I'd like
Simon Willison reflects on how vibe coding and agentic engineering are converging in his own workflow, raising concerns about code review responsibilities as AI coding agents like Claude Code become increasingly reliable. He explores the ethical tension between trusting AI-generated code in production and maintaining software engineering standards.
@dedene: Vibe coding looks easy. Zero upfront design. Zero structure. The reality is: Every broken iteration burns tokens. Every…
A tweet highlights the challenges of vibe coding and promotes a free 50-page guide on transitioning to agentic engineering, covering a new AI-driven software development life cycle.
Vibe Coding Ate My Homework: An evaluation of AI approaches to greenfield software engineering and programming
This paper evaluates the viability of 'vibe coding'—using natural language prompts with AI agents to generate code without human review—for greenfield software engineering tasks, and analyzes existing benchmarks for measuring LLM programming proficiency. The authors develop an evaluation suite for simple Python programming tasks to provide scoped insights.
How to vibe code in science: early adopters share their tips
Scientists are adopting 'vibe coding', a conversational approach using AI tools like LLMs to generate code for data visualization and analysis, speeding up research but requiring caution.
Am I the only one starting to get 'Vibe Coding' fatigue ?
A developer shares their fatigue with 'vibe coding,' noting that while AI agents speed up initial creation, they introduce significant architectural debugging challenges and technical debt in complex repositories.