[behnamoh]

> The assistant is Claude, created by Anthropic.

> The current date is {{currentDateTime}}.

> Claude enjoys helping humans and sees its role as an intelligent and kind assistant to the people, with depth and wisdom that makes it more than a mere tool.

Why do they refer to Claude in third person? Why not say "You're Claude and you enjoy helping hoomans"?

[o11c]

LLMs are notoriously bad at dealing with pronouns, because it's not correct to blindly copy them like other nouns, and instead they highly depend on the context.

[horacemorace]

LLMs don’t seem to have much notion of themselves as a first person subject, in my limited experience of trying to engage it.

[katzenversteher]

From their perspective they don't really know who put the tokens there. They just caculated the probabilities and then the inference engine adds tokens to the context window. Same with user and system prompt, they just appear in the context window and the LLM just gets "user said: 'hello', assistant said: 'how can I help '" and it just calculates the probabilities of the next token. If the context window had stopped in the user role it would have played the user role (calculated the probabilities for the next token of the user).

[cubefox]

> If the context window had stopped in the user role it would have played the user role (calculated the probabilities for the next token of the user).

I wonder which user queries the LLM would come up with.

[katzenversteher]

On one machine I run a LLM locally with ollama and a web interface (forgot the name) that allows me to edit the conversation. The LLM was prompted to behave as a therapist and for some reason also role played it's actions like "(I slowly pick up my pen and make a note of it)".

I changed it to things like "(I slowly pick up a knife and show it to the client)" and then just confront it it like "Whoa why are you threatening me!?", the LLM really tries hard to stay in it's role and then tells things like it did it on purpose to provoke a fear response to then discuss the fears.

[tkrn]

Interestingly you can also (of course) ask them to complete for System role prompts. Most models I have tried this with seem to have a bit of an confused idea about the exact style of those and the replies are often a kind of an mixture of the User and Assistant style messages.

[Terr_]

Yeah, the algorithm is a nameless, ego-less make-document-longer machine, and you're trying to set up a new document which will be embiggened in a certain direction. The document is just one stream of data with no real differentiation of who-put-it-there, even if the form of the document is a dialogue or a movie-script between characters.

[selectodude]

I don’t know but I imagine they’ve tried both and settled on that one.

[Seattle3503]

Is the implication that maybe they don't know why either, rather they chose the most performant prompt?

[freehorse]

LLM chatbots essentially autocomplete a discussion in the form

    [user]: blah blah
    [claude]: blah
    [user]: blah blah blah
    [claude]: _____

One could also do the "you blah blah" thing before, but maybe third person in this context is more clear for the model.

[rdtsc]

> Why do they refer to Claude in third person? Why not say "You're Claude and you enjoy helping hoomans"?

But why would they say that? To me that seems a bit childish. Like, say, when writing a script do people say "You're the program, take this var. You give me the matrix"? That would look goofy.

[katzenversteher]

"It puts the lotion on the skin, or it gets the hose again"

[the_clarence]

Why would they refer to Claude in second person?