Skip to content

Integrating GPT and NARS, a Cognitive Architecture, by Patrick Hammer, PhD

Photo of Pedro Faria
Hosted By
Pedro F.
Integrating GPT and NARS, a Cognitive Architecture, by Patrick Hammer, PhD

Details

Hello AI Brussels members!

This next event is actually produced by the Northwest AGI Forum Meetup, based in Seattle. I thought their next event was so interesting that I reached out to them to see if I could post it here as well. They were kind enough to let us do it, so here it is. This is an online talk. If you are interested in watching, please go to https://www.meetup.com/northwest-artificial-general-intelligence-meetup-group/events/293131059/ and RSVP there. The link to the talk is there as well.

Generative AI is breaking all records and is as hot as technology can get. But can it go the distance and give us AGI? One tantalizing prospect is fusing large language models with cognitive architectures. Patrick Hammer has been pursuing such a goal.

Dr. Hammer will present the following:
A NARS implemented as a GPT model prompted to act like a Non-Axiomatic Logic reasoner, with NARS-based memory and control machinery implemented in Python. This is the first reasoning system implementation that uses GPT for reasoning with long-term memory. Also, it is following NARS principles regarding evidence tracking, memory management, and attentional control which allow the system to operate in a long-term manner while being able to learn and apply new knowledge effectively. In addition, other relevant issues may be discussed.

Features:

  • Natural Q&A interaction with the user
  • The system has no initial knowledge (unless the IncludeGPTKnowledge flag is set) but you can simply teach it
  • The system will make NAL inferences and will raise questions

Patrick Hammer holds a Ph.D. in Computer Science (AI track) from Temple University in Philadelphia, doing much work on the NARS system. He is a Postdoctoral Researcher at Digital Futures. The position is hosted by the Division of Biological Psychology and is associated with the project “Intelligence through Reasoning” which is aimed at enhancing the autonomy of intelligent agents. Much of the work is being carried out within the Digital Futures research center that aims to shape an economically, environmentally, and socially sustainable society through digital transformation. The work is being conducted in a collaboration between the Department of Psychology, Stockholm University, and the Division of Computational Science and Technology at The School of Electrical Engineering and Computer Science at KTH Royal Institute of Technology.

Photo of Artificial Intelligence Brussels group
Artificial Intelligence Brussels
See more events