If you are planning to use vibe coded programs then you better plan for a lot of RAM. Well I say planning when its really being thrust upon you in a lot of cases.

But be extremely mindful when looking at anything touched by Anthropic or OpenAI.

These coding agents have terrible feedback cycles for lag and memory leaks. A particularly egregious one is GPU usage which is absurdly high in most of these apps due to terrible design and react render loop issues. Someone needs to make RL enviroments than punish this.

I will caveat this with saying being wasteful with resources is not new at all. But at this point it seems like no one is doing any amount of basic due diligence.

▲

swordsith an hour ago | parent | next [-]

The source of the bloat is less vibecoding and more architecture missteps and reliance on using web interfaces for everything.

▲

rock_artist a day ago | parent | prev [-]

I think that is a bold statement.

It depends on who’s promoting as well as the stack and the app and the complexity.

To be honest (no pun intended here), I’ve actually benefited from finding leaks and optimizing code paths by such tools. As long as something is measurable and testable you can benefit from AI. Worth mentioning, I mostly do C++ code at my work.

	▲	zamalek 16 hours ago \| parent [-]
		At least so far as Microsoft goes, it is abundantly clear that they do not use LLMs like you claim to. The gp comment is an extremely fair assumption. I'd also wager that people like you are extreme anomalies in general. We are seeing decreasing software quality across the industry. Your statement is the bold one.