I wrote: Robin <mixent...@aussiebroadband.com.au> wrote: > > Multiple copies, spread across the Internet, would make it almost >> invulnerable. >> (Assuming a neural network can be "backed up".) >> > > I do not think it would be difficult to find and expurgate copies. They > would be very large. >
There is another reason I do not think this would be a problem. I expect the hardware for the first sentient AI would be unique. It would be some sort of supercomputer with lots of artificial neural network (ANN) hardware circuits. You could not run a backup copy on another computer, or on something like Google's computer array. Eventually, assuming the sentient AI does not destroy the world, there might be many of these computers, so a backup copy could be run. I asked ChatGPT about this -- ME: Does ChatGDP run on specialized hardware, or on ordinary computers? ChatGPT: As an AI language model, ChatGPT can run on both specialized hardware and ordinary computers. The specific hardware used to train and run ChatGPT varies depending on the scale of the model and the computational resources available. For example, the largest version of GPT-3, which has 175 billion parameters, was trained using a combination of thousands of graphics processing units (GPUs) and tensor processing units (TPUs) on a specialized computing infrastructure provided by OpenAI. However, smaller versions of GPT-3 can be run on ordinary computers with sufficient memory and processing power. Similarly, as a language model, ChatGPT can be run on both specialized hardware, such as GPUs or TPUs, or on ordinary computers, such as laptops or desktops. However, the speed and performance of the model will vary depending on the hardware used.
