Isabelle Levent

The fact that adding keywords like  Let’s Think Step By Step , adding “Greg Rutkowski”, prompt weights, and even negative prompting are still so enormously effective, is a sign that we are nowhere close to perfecting the “language” part of “large language models”.

Even when these paragraphs fail, they make her interested in the story again. She’s curious about this computer-generated text, and it reignites her interest in her own writing.

Whatever the size of the space, someone who comes up with a new idea within that thinking-style is being creative in the second, exploratory, sense. If the new idea is surprising not just in itself but as an example of an unexpected general  type , so much the better.

My lesson from these two examples is that it might be possible to make prompting “invisible” by making it part of the UI, and finetuning output for as much of the writer’s context as possible to make it more useful. Latency matters, and cost matters, which are wonderful because these tend to be “regular engineering” type problems rather than AI

Thoughtful attention to detail requires discipline and objectivity. It entails accepting standards and limitations that forbid the indulgence of impulse or whim. It is this selflessness that, in connection with bullshit, strikes us as inapposite. But in fact it is not out of the question at all. The realms of advertising and of public relations,