An AI model’s response is a long chain of statistically likely next tokens. You experience it as a conversation with something that knows things. It does not know things. It predicts them — very well, most of the time. It does this based on what you feed into its context window. Both of these concepts are apparently very important in how to effectively — or ineffectively — use AI. So they tell me. Or so I’m telling you. Either way, come inside and learn something. Or don’t.
Have a question or feedback? Ford reads every message.