“LLMs not only fail to properly generate correct Python code when default function names are swapped, but some of them even become more confident in their incorrect predictions as the model size increases, an instance of the recently discovered phenomenon of Inverse Scaling, which runs contrary to the commonly observed trend of increasing prediction quality with increasing model size” https://arxiv.org/abs/2305.15507
TBH: lately I've been noticing how easy it is for #SiliconValley#TechnoFascist#VC’s and their incumbent #BigTech distribution partners to deceive humans 🤦🏻♂️
Srsly, thanks for all you do 🙏
Hugely appreciated.