rhdhfjej

Yes, the cost figures published by LLM labs imply a power consumption measured in megawatts for each instance of top performance frontier models. Take the L.

Your brain has a TDP of 15W while frontier LLMs require on the order of megawatts. That's 5-6 orders of magnitude difference, despite our semiconductors having a lithographic feature size that's also orders of magnitude smaller than our biological neurons. You should do some more research.

Remember when they told us in CS class that it's better to design more efficient algorithms than to buy a faster CPU? Well here we are building nuclear reactors to run our brute force "scaled" LLMs. Really, really dumb.

No, he's right. The general public has no idea what "sideloading" even means, but they sure as shit would want to be able to load their own apps if they were asked about it. The terminology is meant to obfuscate the issue.