It makes no sense to me that one would train a chatbot on chatgpt conversations and not filter strings that literally say "openai" and "chatgpt". Extreme incompetence.
Excluding OpenAI/ChatGPT generated content without excluding discourse that mentions OpenAI / ChatGPT such as news articles and industry papers seems like a nontrivial problem to solve at scale.
thorncorona|2 years ago
qarl|2 years ago
Handling the huge number of cases where ChatGPT says something like "As a large language model created by OpenAI" would be very simple.
sertbdfgbnfgsd|2 years ago
spacecadet|2 years ago