My counterargument in favor of 1-1.5x swap: if you, like me, wish to hibernate your Linux PC or laptop, you need at least as much swap space as physical RAM.
Is unified memory practical for a "normal" desktop/server configuration though? Apple has been doing unified memory, but they also have the GPU on the CPU die. I would be interested to know if a discrete GPU plugged into a PCIe slot would have enough latency to make unified memory impractical.
Good idea, maybe I'll add Groq as another option, since I don't have an internal Llama 3.1 flow yet. But I'll still need to keep the others to maintain the diversity of responses.
Given that this a slide deck for a cable company’s advertising arm, it would be entirely plausible that this data comes from the hardware they give customers which is completely customized for their needs. If they were using phone apps, for example, we’d see people asking why the Cox cable app is using their iPhone’s microphone.
My modus operandi for finding a non-obvious RSS feed is to check the Wayback Machine's list of saved URLs and search for "RSS", "feed", or "XML". That normally will find the feed as long as it exists.
reply