Re:Latest ChatGPT 4 System prompt (1,700 tokens)
by ben_w on Wednesday February 07, 2024 @10:57AM
(#39290082)
They explicitly said so, phrasing it as "laziness", on their blog post.
"""Today, we are releasing an updated GPT-4 Turbo preview model, gpt-4-0125-preview. This model completes tasks like code generation more thoroughly than the previous preview model and is intended to reduce cases of “laziness” where the model doesn’t complete a task. The new model also includes the fix for the bug impacting non-English UTF-8 generations.""" - https://openai.com/blog/new-embedding-models-and-api-updates
Re:Latest ChatGPT 4 System prompt (1,700 tokens)
by electroly on Wednesday February 07, 2024 @10:59AM
(#39290105)
That particular line has been in the system prompt for a long time. It's from the Web Browser model prompt and I remember it being there before they merged all the models (DALL-E, Advanced Data Analysis, Web Browser) into a single combined model.
https://github.com/spdustin/ChatGPT-AutoExpert/blob/main/_sy... (check date and history)
Lol - it looks like they got hit by the recent laziness of GPT-4 too.