On Monday, OpenAI employee William Fedus confirmed on X that a mysterious chart-topping AI chatbot known as

Before launching, GPT-4o broke records on chatbot leaderboard under a secret name

submited by

Style Pass

2024-05-15 07:30:03

On Monday, OpenAI employee William Fedus confirmed on X that a mysterious chart-topping AI chatbot known as "gpt-chatbot" that had been undergoing testing on LMSYS's Chatbot Arena and frustrating experts was, in fact, OpenAI's newly announced GPT-4o AI model. He also revealed that GPT-4o had topped the Chatbot Arena leaderboard, achieving the highest documented score ever.

"GPT-4o is our new state-of-the-art frontier model. We’ve been testing a version on the LMSys arena as im-also-a-good-gpt2-chatbot," Fedus tweeted.

Chatbot Arena is a website where visitors converse with two random AI language models side by side without knowing which model is which, then choose which model gives the best response. It's a perfect example of vibe-based AI benchmarking, as AI researcher Simon Willison calls it.

The gpt2-chatbot models appeared in April, and we wrote about how the lack of transparency over the AI testing process on LMSYS left AI experts like Willison frustrated. "The whole situation is so infuriatingly representative of LLM research," he told Ars at the time. "A completely unannounced, opaque release and now the entire Internet is running non-scientific 'vibe checks' in parallel."