![Thumbnail of Why "Prompt Engineering" and "Generative AI" are overhyped](https://substackcdn.com/image/fetch/w_1200,h_600,c_fill,f_jpg,q_auto:good,fl_progressive:steep,g_auto/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F681286aa-fe56-42a5-8031-71308e99c829_952x815.png)
added by Isabelle Levent · updated 1y ago
added by Isabelle Levent · updated 1y ago
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 pr
... See moreIsabelle Levent added 1y ago
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”.
Isabelle Levent added 1y ago