@bentlegen: to make *actually* good software, you have to use it a lot but many people are spending more time in their coding agent…
Summary
Developer Ben Tlegen observes that building truly good software requires extensive personal use, but warns that many developers are now spending more time inside AI coding agents than in the actual applications they are creating.
View Cached Full Text
Cached at: 09/06/26, 08:51 PM
to make actually good software, you have to use it a lot
but many people are spending more time in their coding agents/factories than in the apps they’re building - so they won’t
Similar Articles
Is AI agents making it easier to build software than to understand it?
A developer reflects on how AI coding agents can rapidly build and modify software, but developers often lose understanding of the codebase architecture and decisions, creating a new engineering challenge.
AI coding tools are getting good enough to actually ship things, which is kind of a problem for learning
A developer reflects on how AI coding tools boost productivity but may hinder deep learning, as users ship code they don't fully understand, raising questions about skill development.
@omarsar0: Nice report on agents beyond code generation. Here is why it matters: Coding agents raise how much code gets written. T…
A report synthesizes field studies to argue that while AI coding agents increase code output, gains shrink in shipping reliable software due to bottlenecks in review, integration, and cost management.
@saranormous: https://x.com/saranormous/status/2064510215056400652
Despite rapid advances in AI coding agents like Devin, which have dramatically increased code writing and shipping, the article argues that the most valuable aspects of software engineering remain illegible to benchmarks and require human judgement and organizational coordination that cannot be easily automated.
@tunguz: Here is one big reason why this matters. Time spent on non-LLM inference tasks is only going to increase. However, tool…
A post highlights that 42% of time in modern agentic coding is spent on CPU-based tool use, which is inefficient and presents a major opportunity to redesign these tools for AI agents.