“Our maps are still maps, approximating the landscape of truth from the territories of the knowable — incomplete representational models that always leave more to map, more to fathom, because the selfsame forces that made the universe also made the figuring instrument with which we try to comprehend it.” Source
Aggregators instead of Oracles
“When I first began tinkering with a software program that eventually gave rise to the idea of the World Wide Web, I named it Enquire, short for Enquire Within upon Everything, a musty old book of Victorian advice I noticed as a child in my parents’ house outside London.
ENQUIRE was influenced by a book that claimed to be an oracle - to have the answer for every question, to promise the ‘suggestive magic’ that so excited the young Berners-Lee. But that promise was ultimately unfulfilled. Berners-Lee recognised that what he needed to build was not an oracle but a map - a web of paths and connections linking information and guiding users as they research, not an all-knowing entity that gives us a single answer.
- The difference between screen-based search and voice based search is the difference between a map and an oracle - on screens we’re given a list of search results to navigate, whilst in voice based search we’re not read a list of potential links - we’re given an answer.
- Temperature gives us variability, and this is what makes LLMs more of a walk through a map of latent space than a single true answer
- 0, which produces perfect fidelity to the physics, i.e., always selecting the most likely next word
- 0.8, which slightly weakens the gravitational pull in its textspace, so that less common words will be chosen more frequently
- Predictions are paths within a multidimensional space of knowledge, helping us map out those spaces and understand its hills and valleys
- How do we show the map when the map itself is in thousands of dimensions?
See also: search as oracle