minus-squaretrent@kbin.socialtoTechnology@beehaw.org•Future LLMs will be progressively worse - and possibly change how humans writelinkfedilinkarrow-up6·1 year agoThat’s not a joke – that’s exactly how a lot of the smaller open-source LLMs are trained. Orca (paper) is trained between GPT-4 and GPT-3.5-turbo linkfedilink
That’s not a joke – that’s exactly how a lot of the smaller open-source LLMs are trained. Orca (paper) is trained between GPT-4 and GPT-3.5-turbo