How to Outwit Generative AI

rw-book-cover

Metadata

Author: Benjamin Riley from Cognitive Resonance
Full Title: How to Outwit Generative AI
Category: #articles
Summary:: Generative AI models often produce unpredictable and varied responses, which can make them unreliable. While they can excel in some tasks, such as coding and math, they still struggle with complex problems and reasoning. Understanding how these models work is crucial, as they rely on probabilities rather than deterministic answers.

But then when you go into production with an LLM, there is no text at the end. So you’re presenting the AI with the user’s query or prompt, and you’re essentially, as far as the model is concerned, telling it, “Here is some text I cut off the end of, fill in the back end of it.” But that’s not actually what happened. You didn’t actually cut off the end of anything. And I believe that this has important consequences for for how we can expect models to behave, and also how we can expect to control how they behave. (View Highlight)
Let’s stick with the the bird detector, because I think it’s important for people to understand in almost a philosophical sense, that with traditional machine learning there’s an objective definition of right and wrong that’s been classified: This is a bird, this is not a bird. The model is trained on that and compares against that objective truth. Whereas with generative AI, when we give it prompts, we’re asking it to provide something where there is no objective truth to measure against. It’s like we’ve asked it to pretend there’s something out there in its training that that exists. (View Highlight)