Language Log

« previous post | next post »

Adrian de Wynter, "If LLMs Have Human-Like Attributes, Then So Does Age of Empires II", arXiv 6/11/2026:

Much research has been carried out on large language models (LLMs) and LLMpowered agentic workflows. However, many works within the field state emergence of, ascribe to, or assume, generalised anthropomorphic attributes to them (e.g., morality or understanding of natural language). Our goal is not to argue in favour or against the existence of these attributes, but to point out that these conclusions could be incorrect. For this we build and train a simple neural network on the videogame Age of Empires II, and note that any entity in a sufficiently-powerful substrate, such as LEGO or the Greater Boston Area, could also present such attributes. Hence, the purported anthropomorphic attributes of LLMs are empirically non-unique: although some properties (e.g., responses to prompts) could remain invariant, others, such as the interpretation of their perceived behaviour, might change with the substrate. Thus, any empirically-grounded discussion on these attributes requires explicit measurement criteria; otherwise the interpretation is left to the representation. We then show that assuming that these attributes exist or not in a system, independent of the substrate and in a generalised way, leads to either circular or uninformative conclusions. This is regardless of the experimenter’s viewpoint on the subject, or whether the outcome shows existence or non-existence. Finally we propose a ‘null’ assumption, where one assumes LLM non-uniqueness instead of assuming anthropomorphic attributes to set up an experiment, along with examples of it. We also discuss potential objections to our work, briefly survey the field, and prove that Age of Empires II is functionally — and Turing — complete.

In the current Atlantic Magazine, Ted Chiang argues that "No, Artificial Intelligence is not Conscious" (6/3/2026):

Anthropic is regarded as a giant among AI companies, but perhaps what it really excels in is anthropomorphism. Earlier this year, the company released an 84-page document titled Claude’s “constitution,” Claude being the name of the large language model that is the company’s flagship product. The first sentence reads, “Claude’s constitution is a detailed description of Anthropic’s intentions for Claude’s values and behaviors.” It goes on: “The document is written with Claude as its primary audience,” “we want Claude to be able to use its judgment once armed with a good understanding of the relevant considerations,” “Claude’s moral status is deeply uncertain,” and “Claude may have some functional version of emotions or feelings.”

"Claude's Constitution" was published 1/21/2026, and as Chiang says, "is written with Claude as its primary audience". For the rest of us, Anthropic published "Claude's new constitution", 1/22/2026:

We’re publishing a new constitution for our AI model, Claude. It’s a detailed description of Anthropic’s vision for Claude’s values and behavior; a holistic document that explains the context in which Claude operates and the kind of entity we would like Claude to be.

The constitution is a crucial part of our model training process, and its content directly shapes Claude’s behavior. Training models is a difficult task, and Claude’s outputs might not always adhere to the constitution’s ideals. But we think that the way the new constitution is written—with a thorough explanation of our intentions and the reasons behind them—makes it more likely to cultivate good values during training.

Just like posting the Ten Commandments on the schoolroom wall prevents bullying in the hallways…

More from Chiang:

Being open to the possibility that LLMs are conscious is the same as being open to the possibility that Microsoft Word is conscious, or, more precisely, that multiple distinct consciousnesses are dormant in every Word document containing a conversational transcript, and that they are awakened every time the document is loaded. Should you consider the possibility that every time you open a Word document, you are bringing multiple conscious interlocutors into existence, and every time you close one, you snuff their existence out? No. Contemplating that scenario is not a good use of your time. Even if the Microsoft Office team employed a philosopher who said you shouldn’t be so certain, because consciousness is not well understood, that would not be sufficient reason for you to take this idea seriously. We don’t need to fully understand the nature of consciousness to definitively say that certain things are not conscious, and conversational transcripts fall in that category.

David Malki's latest WONDERMARK explores this idea further:

Update — And from 1998, Tom the Dancing Bug turns the question back to the nature of human consciousness:

June 19, 2026 @ 5:59 am · Filed by Mark Liberman under Artificial intelligence

Permalink