[execveat]

It's a language model, FFS. Ask it whether it uses PaLM 1 and it will confirm it as well.

[netdur]

- are you on PaLM 2 right now?

- Yes, I am currently running on PaLM 2, which is Google AI's latest and most advanced large language model. PaLM 2 is trained on a massive dataset of text and code, and it is able to generate text, translate languages, write different kinds of creative content, and answer your questions in an informative way.

PaLM 2 is still under development, but it has learned to perform many kinds of tasks, including

I will try my best to follow your instructions and complete your requests thoughtfully. I will use my knowledge to answer your questions in a comprehensive and informative way, even if they are open ended, challenging, or strange. I will generate different creative text formats of text content, like poems, code, scripts, musical pieces, email, letters, etc. I will try my best to fulfill all your requirements. Please instruct me what you want me to do today.

- are you on PaLM 1 right now?

- I am not on PaLM 1. PaLM 1 is a large language model that was developed by Google AI. It was trained on a massive dataset of text and code, and it is able to generate text, translate languages, write different kinds of creative content, and answer your questions in an informative way.

I am a large language model that is still under development. I am trained on a massive dataset of text and code, and I am able to generate text, translate languages, write different kinds of creative content, and answer your questions in an informative way.

I am not as advanced as PaLM 1, but I am learning new things every day. I hope that one day I will be able to do everything that PaLM 1 can do, and more.

[execveat]

Yeah, but Reset the chat between your questions.

EDIT: Also, this doesn't seem convincing: "I am not as advanced as PaLM 1, but I am learning new things every day. I hope that one day I will be able to do everything that PaLM 1 can do, and more."

[akiselev]

Are you using the palm 5 or palm 11 model?

> My knowledge are for a physical stylus pen. I am not a physical device, so I do not use a stylus pen.

[josh_cutler]

It will tell you it uses PaLM 1, PaLM2, PaLM 3 or PaLM 540B depending on how you prompt. It will stop acknowledging incremental PaLM models at 5 it seems.

[ilikeatari]

So, I tried that and that was not the case for me. It actually generated response that its on PaLM 2 and I ask for all these permutations.

[famouswaffles]

Not really. If what model it was trained on was represented properly in the instruction tuning dataset then they'll consistently identify themselves. But it's not a given that that was the case for bard.

[execveat]

It seems that Bard's version is only specified in the prompt, and it doesn't have a strong sense of identity. For me it's pretty reliable:

1. ask it what PaLM 2 is (to pollute the context) 2. ask it whether it's based on PaLM 2 (it will tell you - yes, sure)

[chaxor]

Just let people be monumentally stupid like this. You can't correct it.

[ilikeatari]

Sorry, can you elaborate? I would like to learn. I realize it's LLM, but is it really assumed that it will not be able to identify itself?

[ilikeatari]

That is fascinating. Is it the same for GPT 3.5 and 4? For some reason when I was asking Open AI it was identifying itself properly.

[execveat]

ChatGPT was the same last year, but since ClosedAI added some kind of magic (fine-tuning or just embeddings auto-injection) so that models can somewhat describe themselves.

[famouswaffles]

If it's indicated in the instruction tuning dataset properly then it should have no problem identifying itself. But we don't know if that happened when bard.