The 'AI-generated pseudo-spec' is becoming a massive productivity killer. Non-technical managers prompt an LLM, get a highly confident 5-page document with chosen libraries, and think they've done 80% of the work. But as a developer, you now have to spend hours debugging and debunking hallucinated architectures just to prove why the AI's approach doesn't fit the existing codebase. It completely shifts the burden of actual product management into AI-babysitting for the dev team.
I was discussing a change we wanted to make to some tables in one of the DBs, but it would require a lot of effort because of the sheer size. Anyway, after saying how much effort would be required the response I got was to “please ask ChatGPT.” It gave a slightly different response, but changed it after I presented it with my solution and agreed that was the better approach. Just… sigh
"Apologies, you're absolutely right. My initial strategy indeed would have caused a massive database bottleneck because it would lock the entire table. This could result in downtime for the application. Let me know if you'd like me to make a step-by-step plan to implement your solution."