LARRUZ tests Meta's new open-source Llama 2 model, asking it to write an essay about penguins. The output looks different from GPT-3.5 and GPT-4, and Llama 2 may outperform GPT-3.5 in many cases, though the verdict isn't final yet.
Meta just surprised us with a brand new open source language model called llama2. This thing is the best open source model we have, and in many cases they claim this to be better than GPT 3.5, but we can simply test this. Write me an essay about penguins. Alright, let's see how this goes. And already having run this prompt hundreds of times across all different language models, I can say the structure is very different and distinct from GPT 3.5 and GPT 4 here. I don't feel like I've explored this enough to give you guys objective opinion on how the outputs differ, but certainly these are very usable results. Just like GPT GPT 3.5 would give you spoken in a different tone and voice.
