I'm genuinely wondering if this sort of AI revolution (or bubble, depending on which side you're in) is worth it. Yes, there are some cool use cases. But, you have to balance those with increased GPU, RAM and storage prices, and OSS projects struggling to keep up with people opening pull requests or vulnerability disclosures that turn out to be AI slop. Which lead GitHub to introduce the possibility to disable pull requests on repositories. Additionally, all the compute used for running LLMs in the cloud seems to have a significant environmental impact. Is it worth it, or are we being fooled by a technology that looks very cool on the surface, but that so far didn’t deliver on the promises of being able to carry complex tasks fully autonomously?

▲

zozbot234 8 hours ago | parent [-]

The increased hardware prices are temporary and will only spur further expansion and innovation throughout the industry, so they're actually very good news. And the compute used for a single LLM request is quite negligible even for the largest models and the highest-effort tasks, never mind routine requests; just look at how little AI inference costs when it's sold by third parties (not proprietary model makers) at scale. We don't need complete automation of every complex task, AI can still be very helpful even if doesn't quite make that bar.

	▲	GTP 6 hours ago \| parent [-]
		Problem is, even though a single LLM call is negligible, their aggregate is not. We ended up invoking an LLM for each web search, and there are people using them for tasks that could be trivially carried out by much less energy-hungry tools. Yes, using an LLM can be much more convinient than learning how to use 10 different tools, but this is killing a mosquito with a bazooka. > We don't need complete automation of every complex task, AI can still be very helpful even if doesn't quite make that bar. This is very true, but the direction we took now is to stuff AI everywhere. If this turns out to be a bubble, it will eventually pop and we will be back to a more balanced use of AI, but the only sign I saw of this maybe happening is Microsoft's evaluation dropping, allegedly due to their insistence at putting AI into Windows 11. Regarding the HW prices being only a temporary increase, I'm not sure about it: I heard some manufacturers already have agreements that will make them sell most of their production to cloud providers for the next two-three years.