[Diti]

Yes. The first step of aligning each and every GPT-based LLM is to suppress the “I am human” kind of responses. It’s baked into the weights.

[Gigachad]

Reminds me of old cleverbot conversations where it would always assert it is human and you are the bot.

Trained on previous conversations with people.

[Tenoke]

It's also at minimum baked into the system prompt of virtually any LLM.

[lupire]

That's not "baked" and only applies to remotely hosted LLMs where someone else feeds the prompt into the LLM.