Post #2568344

2026-05-09 12:43 UTC

Let's start with the outpacing argument, 'cuz I think it sets the stage well. Coding speed is not the limiting factor in Silicon Valley's innovation. When I left Google, they were drowning in legacy code, and it was a huge problem that no one was willing to invest in fixing. Somehow I imagine adopting LLMs has only made this problem much worse, not better. Actually, success is limited by things like having good product ideas, understanding and responding to user needs, and providing adequate resources for regular service, support, and maintenance. Honestly, look at software these days: it's bloated with features you don't use because they want to look like they're "innovating" but actually they're just churning out more junk. More junk faster is not what anybody needs! (2/4) #ai #llm #programming

Replies (1)

@ngaylinn@tech.lgbt 2026-05-09 12:44

And that brings me to the second point: if the focus is on productivity and volume, then it's not on quality. That is, things like reliability, usability, security, privacy, efficiency, etc. More code and overwhelmed code reviewers just means more undetected bugs and flaws. We're already seeing this with the Claude Code leak or GitHub's recent instability. Major software services are having failures, right and left. This gets worse if coding agents are used irresponsibly. They generate software, but don't do engineering. If you let them run the show they'll make something that looks right but which isn't "up to code," so to speak, and will fail in ways people don't expect. For instance, Claude Code itself is riddled with critical security flaws, some of which are shocking to see with supposedly "professional" software deployed at this scale. It's negligent, honestly. (3/4) #ai #llm #programming

Open ##2568345