Hacker News new | ask | show | jobs
by Kurtz79 308 days ago
"what model are you?"

ChatGPT said: You're chatting with ChatGPT based on the GPT-4o architecture (also known as GPT-4 omni), released by OpenAI in May 2024.
1 comments
pjerem 308 days ago
Actually this trick have been proven to be useless in a lot of cases.

LLMs don’t inherently know what they are because "they" are not themselves part of the training data.

However, maybe it’s working because the information is somewhere into their pre-prompt but if it wasn’t, it wouldn’t say « I don’t know » but rather hallucinate something.

So maybe that’s true but you cannot be sure.

link
dpoloncsak 308 days ago
If you believe 'leaked system prompts', it tends to be part of the system prompt.

I believe most of these came from asking the LLMs, and I don't know if they've been proven to not be a hallucination.

https://github.com/jujumilk3/leaked-system-prompts

link
efilife 308 days ago
It's injected into their system prompt
link
seba_dos1 308 days ago
...which is useless when the model gets changed in-between responses.
link