Hacker News new | past | comments | ask | show | jobs | submit login

Plot twist!

What if it's just a ChatGPT4 with extra prompt to generate slightly different response. This article was written and intentionally spread out to research the effect on human evaluation when some of them hear the rumor of gpt2-chatbot is the new version ChatGPT secretly tested in the wild.




I don't think a magical prompt is suddenly going to make any current public model draw an ASCII unicorn like this thing does. (besides, it already leaks a system prompt which seems very basic)


https://imgur.com/a/z39k8xz

Seems like it's not too hard an ask.


It’s curious you and the other guy got the almost exact same response for the unicorn.


It works fine on the current chatgpt 4 turbo model https://chat.openai.com/share/d00a775d-aac7-4d14-a578-4e90af...


On GPT-4 release I was able to get it to draw Factorio factory layouts in ASCII which were tailored to my general instructions.

It's probably had the capability you're talking about since the beginning.




Consider applying for YC's Summer 2025 batch! Applications are open till May 13

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: