Re:OpenAI builds first chip with Broadcom and TSMC, scales b...
by soulofmischief on Thursday October 31, 2024 @02:15PM
(#42009711)
They've presented a hypothesis warranting further study.
Here is an article where a model's learned ability to carry out modular addition is recovered. https://arxiv.org/abs/2301.05217
As you can see, the jury's still out.
"We hypothesize that this decline is due to the fact that current LLMs are not capable of genuine logical reasoning; instead, they attempt to replicate the reasoning steps observed in their training data."