Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
OpenAI is reportedly testing two new models, named 'im-a-good-gpt2-chatbot' and 'im-also-a-good-gpt2-chatbot', as indicated by multiple user observations on the chat.lmsys platform. These models, referred to as Model A and Model B, surfaced following a joke by OpenAI's CEO, Sam Altman, on May 5th, a Sunday. Users have conducted tests, suggesting that Model A performs significantly better than its counterpart.
late last night im-a-good-gpt2-chatbot reappeared on chat.lmsys, along with another model named im-also-a-good-gpt2-chatbot i stayed up all night to bring you the alpha ran a bunch of tests, here's the results: im-a-good-gpt2-chatbot: • very strong, definitely better than… https://t.co/0hCZrRqsdF
2 models A) im-a-good-gpt2-chatbot B) im-also-a-good-gpt2-chatbot hereafter called A and B Suspected to be OpenAI models, now available in lmsys arena Why suspected? > Sam Altman made a joke on May 5th Sunday https://t.co/RfBV2UGRtg
It seems like OpenAI might actually be testing two models! "im-a-good-gpt2-chatbot" "im-also-a-good-gpt2-chatbot" https://t.co/fLE97Cv8nd
