The Alignement AI Lab just published OpenChat 3.5, which is outperforming ChatGPT (march version) on most benchmarks apart from MMLU (67.3% vs 64.3%) & BBH-CoT (70.1% vs 63.5%).
It seems very good but it thinks that it's ChatGPT:
"Who are you?
I am an AI language model named ChatGPT, developed by OpenAI. I am designed to engage in conversations and provide information on a wide range of topics."
Edit: I can see in the paper they linked it mentions using ShareGPT data
2 comments
[ 3.2 ms ] story [ 24.5 ms ] thread"Who are you?
I am an AI language model named ChatGPT, developed by OpenAI. I am designed to engage in conversations and provide information on a wide range of topics."
Edit: I can see in the paper they linked it mentions using ShareGPT data