They’re definitely not. Hard drives use a fraction of the energy a single LLM prompt does. A study calculated that every 100 words uses an entire water bottle’s worth of water. That’s a lot of cooling for 100 words. It’s very likely that these companies use several gpus for every single prompt, meaning huge servers for just a few users.

Meanwhile the internet archive has archived a significant portion of the internet with nary a data center in sight.

You can compress video. You can’t compress the energy needed to generate output.