Minotaur AI reasons like an LLM without a language model or GPU
Achieving AI-style reasoning without an LLM
Minotaur, built on the ELC architecture, handles deduction, induction, abduction, diagnosis, belief revision, and counterfactual reasoning with a single operation on a single network, running on one ordinary CPU core at roughly a quarter-second per question. On blind tests written by people who never saw its code, it matched a current language model on a police-interview scenario where questions alter the witness's memory, and on learning, diagnosing, and predicting systems from data alone.
Each way of getting a machine to reason has had a price: the ones that reason exactly need the model handed to them; the ones that learn from data give you no structure to reason on; the one that reads the prose needs a data centre, and can't certify its answers.
- jstanley
I can't see where you can try this out, so at the moment it's a lot of claims and no real evidence. Also the text feels like it was written by an LLM.
If it's really such a small model why not provide a web interface where we can test it for ourselves?
This feels like high risk of being crackpottery.
- iterance
The associated paper is (I will say generously) not forthcoming: https://zenodo.org/records/23526702
I can also find no working model. I expect this may be disregarded for now.
- kangalioo
Never seen that one before:
"Insufficient Storage
The method could not be performed on the resource because the server is unable to store the representation needed to successfully complete the request. There is insufficient free space left in your storage allocation.
Additionally, a 507 Insufficient Storage error was encountered while trying to use an ErrorDocument to handle the request."