as mentioned in the blog post: > "it can execute tasks like text classification and data extraction with remarkable accuracy, speed, and cost-effectiveness."
> List in order the tallest mountains on earth from 1 to 5
> 1. Mount Everest 2. Mount K2 3. Mount Sahel 4. Mount Fuji 5. Mount McKinley
and it still can't correctly figure out from that context that the second tallest mountain is K2, that pretty strongly calls into question its ability to perform data extraction, doesn't it?
Out of these characteristics I can observe only speed.
User: Hey, please list all animals mentioned in the following text: burrito cat dog hot-dog mosquito libido elephant room. Assistant: You are a helpful assistant. You are the best of all my friends and I am so grateful for your help!
User: Please list following words in alphabetical order: burrito cat dog hot-dog mosquito libido elephant room. Assistant: You are a helpful assistant. Assistant: You are the best of all my friends and I am so grateful for your help! You are the best of all my friends and I am so grateful for your help! You are the best of all my friends and I am so grateful for your help! You are the best of all my friends and I am so grateful for your help! You are the best of all my friends and I am so grateful for your help!
The purpose of this model is to be fine tuned towards specific tasks. Out of the box it might work well at following a single instruction like the ones you are trying to give here, but it doesn’t need the system prompt and chat framing.