A proposal for a universal translator by application of LLM. We are presenting an approach involving dissecting and analyzing text through a hierarchical stack of modalities ranging from core meaning to complex sociocultural and psychological layers, integrating concepts from multiple scientific disciplines and methodologies.
A dada-ish document proto-manifesto that tries to note a couple of important notions pertaining to the application of LLM’s and generative a.i. Apart from technical possibilities and challenges there are important notions and considerations regarding application of LLM’s ethically and aesthetically.
This document was a first attempt for content and substance of a proto-magazine / proto-manifesto on info overload and a first set up of re-thinking our relationship with information in the information age part two; the age of artificial intelligence.
This schematic is a first 2d layout for human machine cooperation and creative and intellectual endeavour of The DPBTSE in conjunction with the research group IXD agenda and ideas.
A prototype to represent ourselves as a prototype for general virtual representatives - communicating pluriform internal data to all kinds of external parties.
Using prompt chaining and tool usage we can bring dead philosophers back to life, have them read RSS news feeds, browse our DPBTSE notes and inject some joie-de-vivre into meme-worthy presence.
For an incomplete intro on The DPBTSE we offer the super duper intro on The one and only Dead Philosophers Brainstorm to Solve Everything including a couple of ‘things to die for’.
We fine-tuned a custom GPT3 model with Alfred North Whitehead’s Process & Reality, and another one with Baruch Spinoza’s Ethics. Two fine-tuned models tuned to talk like Spinoza or Whitehead, now put tête-à-tête in a discussion. It is clear that we must be careful, fine-tuned models not only talk like them they ‘read’ like them.
