I've seen this many times in GPT-4 base> you make a seemingly non-intrusive intervention> the model *does not continue the interrupted thread* and instead goes "WHO THE FUCK IS THERE"Llama 405B base seems less prone to this behavior but I haven't tested it outside Discord much https://t.co/WHTjqhEUD1
cited on: gpt-4-base · llama-3-1-405b-base
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.