Common sense as a pre-prompt:
The process of creating smarter artificial assistants makes it obvious just how much any human is an expert in the world around us.
Many users of intelligent machines to find themselves frustratingly having to spell out obvious details they did not even consider as factors because they are common sense.
LLMs have the benefit of training on language which incorporates so much common sense that AI ends up learning a lot of it as a byproduct of learning how language works.
Aside from training, there is context, and that has to be more adaptable than pure reasoning or rules. One way we approach this is prompt engineering and pre-prompting; Nudging the AI to think in a specific way regardless of the question in order to be more appropriate for the context.
In digesting any piece of information, how much pre-prompting goes on in our brains? How much factual, social, inferential, and heuristic information is involved in an instant? How much is added or subtracted without fundamentally changing the entire thinking process?
What goes in your pre-prompt?
The future is bright,
Nawar
#ai #promptengineering #prompting #artificialintelligence #philosophy #language
ABOUT THE AUTHOR
Nawar Kamel is CEO and Co-Founder of Experto AI Inc., and licensed Canadian lawyer in Ottawa, ON, Canada.
Nawar started his academic path studying philosophy and went on to get his masters in philosophy focusing on social contract theory from York University. Nawar graduated from the University of Ottawa Faculty of Common Law and was a litigator spending his days fighting in the courts on behalf of his clients until he went on to found Experto AI Inc., which was established to create AI tools geared towards lawyers and legal researchers.