Get the latest tech news
The Clever Hans Effect, Iterative LLM Prompting, and Socrates' Meno
Intelligence in Collaboration
Although modern AI models are undeniably useful, and many companies claim to be pursuing artificial general intelligence (AGI), it is unclear whether recent advancements are properly positioned to address the initial question posed by McCarthy. In addition to rendering the Turing test nearly obsolete, the humanistic nature of a model that communicates in seemingly novel and expressive ways has led many to mistake the world’s largest magic 8-ball for a thinking machine—an effect worsened by the apparent improvements that arise when repeatedly prompting an LLM in a manner akin to the Socratic method presented in Meno. For example, when iteratively prompting an LLM to refine a piece of writing, the model produces outputs that mirror the patterns and probabilities within its training data, moving closer to the desired result only if guided by user input.
Or read this on Hacker News