News for hackers. Stuff that matters.
Re:ChatGPT's API Is So Good and Cheap, It Makes Most Text Ge... by NBJack on Saturday March 11, 2023 @04:40PM (#35113033)
The fun part is when a LLM hits that small probabiliy where they decide to go 'offscript'. It can result in a beautifully terrifying cascade of grammatically acceptable nonsense, and joe fun it would be in a legal document. We go from a loan for a home to a generous offer that includes a unicorn, a purple dishwasher, a unicorn, and a few dangling participles at the going market rate, all for the low low rate of 555.555.1212. [END TOKEN]--- WASHINGTON, D.C. President Trump today met with lawmakers to
Re:ChatGPT's API Is So Good and Cheap, It Makes Most Text Ge... by cs702 on Saturday March 11, 2023 @04:56PM (#35113189)
I laughed really hard -- after trying to make sense of your comment!

Thank you for posting this :-)

Re:ChatGPT's API Is So Good and Cheap, It Makes Most Text Ge... by sebzim4500 on Saturday March 11, 2023 @05:37PM (#35113528)
I think the hope is that as LLMs get larger these issues will go away. Certainly there are issues with GPT-2 that completely went away when moving to larger models.

Honestly, I haven't even seen GPT-3.5-turbo exhibit this behavior myself, although I am willing to believe it could happen. Llama 7B, however, goes off-script constantly.