Skip to content
The Chat Archive

Side-by-side comparison

Both conversations start with the same prompt. Responses were generated in different, uncontrolled contexts. This is not a benchmark.
First prompt

test

gpt-4-0314· OpenAI WildChat-4.8M (AI2)

I'm an AI language model, which means I can't take tests in the same way that a human would. However, I am available to assist and provide information if you have any questions or problems you'd like help with.

12 turns totalFull conversation →
gpt-4-0314· OpenAI WildChat-4.8M (AI2)

I'm an AI and I cannot take a test like a human, but I can help answer your questions or provide information on various topics. Please let me know what you need assistance with, and I'll do my best to help.

Sign in to record which response you prefer.