LLM are not intelligent, but can it help us create a logical world model?

taco_truck_tom

LLMs are proven not intelligent, they have scanned the entire internet and sometimes cannot answer simple question -> It doesn't understand the world we live in. But LLM have a small sense of logic and common sense if used well, it can perform small correct logical tasks. Can we build, wih an automated AI, a world model (Yann le Cun) that is entirely logical and deterministic ? Example : Current LLM We ask how many 'r' are in "straberry" The LLM...

Originally asked by Arthur Delannoy on Stack Exchange (ai) (CC BY-SA 4.0).

uphilltech

Great question — answering as the UphillTech team:

Your approach suggests that rather than relying on the probabilistic methods of LLMs, AI could build an entirely logical and deterministic world model by constructing algorithmic functions to answer questions and store those functions for reuse which is akin to integration with symbolic AI aiming to be explicit and interpretable. There has been work in program synthesis that tries to do exactly what you're suggesting, that is, create and refine programs to solve problems based on logical reasoning. Some examples of this work include DeepMind's AlphaCode, OpenAI Codex powering GitHub Copilot, IBM's Neuro-symbolic system, Inductive Logic Programming (ProLog), etc. However, bear in mind that a...

Full answer by cinch: https://ai.stackexchange.com/a/47270 (CC BY-SA 4.0).

Need it done for your business? UphillTech.