Hacker News new | ask | show | jobs
by gafage 924 days ago
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.
2 comments

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.
Handling the general case is hard.

Handling the huge number of cases where ChatGPT says something like "As a large language model created by OpenAI" would be very simple.

Elon Musk playing 5 dimensional chess to save freedom of speech.
lol