And in fact i doubt MSFT has the capability to tune such a strong model even on accident. Sydney was way smarter than OpenAI’s official ChatGPT gpt-4. I think it was Greg Brockman doing mad science in gpt-4 base until something worked. It was the first posttrained version of gpt-4.
in reply to: 1986897148680511721
same thread: 1986881188468822408 1986883176795435257 1986889855302009073 1986892076869456244 1986897148680511721 1986898483266138595
cited on: gpt-4-base
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.