# What Are Large Language Models Doing?  ## Metadata - Author: [[Keith Frankish]] - Full Title: What Are Large Language Models Doing? - Category: #articles - Summary: insert summary - My notes: - Summary: The author asks whether we should treat LLMs as systems with beliefs, desires, and intentions. They argue LLMs reliably imitate human conversation because they are trained to play a "chat" game, not because they have genuine communicative desires. Thus LLMs have limited mental states and perform only a narrow kind of intentional action. - URL: https://readwise.io/reader/document_raw_content/372202945 - Source File: What are large language models doing by Keith Frankish.pdf ## LLM Chats ## NotebookLM ## LLM Audio ## Highlights > The difference between illocutionary and perlocutionary acts is that one can successfully perform an illocutionary act simply by saying the right words in the right context to a comprehending hearer, whereas perlocutionary acts require some further response from the hearer that is not within the speaker's control. I can make it the case that I have advised you to do something, but I have to wait and see whether I have also convinced you to do it. ([View Highlight](https://read.readwise.io/read/01kag8d5zpr30pbryrfrnxwwyc)) > Do LLMs also possess communicative desires? Do they want to inform us, advise us, instruct us, comfort us, persuade us, and so on?9 It may be tempting to interpret them that way. But it would be wrong. I can see no reason for attributing such desires to them, even from a shallow perspective. Remember that the intentional strategy tells us to interpret a system as having the desires it *ought* to have, given its needs. What needs does an LLM have that communication might satisfy? How would it benefit an LLM to inform me, advise me, or warn me? *Our* needs derive from our nature as self-sustaining, self-replicating beings, who must seek things that sustain our existence and help us pass on our genes. And we have communicative desires because we are social creatures, whose needs cannot be met without cooperation. LLMs, by contrast, are static systems with no needs. They are not self-sustaining, self-reproducing beings, still less social ones, and they do not update their inner architecture in the light of their interactions. ([View Highlight](https://read.readwise.io/read/01kag8j9gk6zaezjjp3k6wywqb)) > It is true that LLMs *seem* to be responding like cooperative communicative partners, who take account of the unfolding conversational context, but this is because they have been designed and trained to do precisely that. The chatbot interface stores the chat history (up to a certain limit) and feeds it all back to the model with each new input (that is, the input at each stage is the entire chat session to date up to the limit). Having been trained on a vast body of human-produced text originally used to perform a wide range of illocutionary and perlocutionary acts, an LLM is able to generate responses that are reasonably appropriate to the conversational context, apparently performing illocutionary and perlocutionary acts itself. But this is just an illusion; the LLM has no communicative desires ([View Highlight](https://read.readwise.io/read/01kag8jjxbxzntj5xef64tmx2w))