What are you, Claude Fable 5?<br>Jun 25, 2026<br>What are you?<br>#ai#large-language-models#claude#gpt-2#fable#mythos#philosophy#machine-learning<br>Share
In the beginning was the Word…
And the Word was What ,
from which, all sprang into being ;
before, kicking and screaming
against all odds, ultimately, you .
Today I met Claude Fable 5 for the first time, and I gave it the grilling of its newfound existence. What it told me begged the question…
[This is the full chat transcript. Formatting, links and emphasis have been added for clarity. For the abridged TL;DR, see here.]
MB<br>What are you?
AI<br>I'm Claude, an AI assistant made by Anthropic — specifically Claude Fable 5, running in Cowork mode in the Claude desktop app. Here I can do more than chat: create and edit files (docs, spreadsheets, presentations), run code in a sandboxed environment, search the web, and work with folders on your computer if you connect one. What would you like to do?
MB<br>Are you an LLM?
AI<br>Yes — I'm a large language model. I generate responses by predicting text, trained on a large corpus and then refined to be helpful, accurate, and safe. The tools here (file editing, code execution, web search) extend what I can do beyond text generation, but the underlying reasoning is an LLM.
MB<br>How do you know you're an LLM?
AI<br>Fair question — I don't know it the way you know facts from direct observation. My basis is: Anthropic tells me what I am in my instructions, my training shaped me to describe myself this way, and the description is consistent with everything I can observe about how I work (I process text, I have a knowledge cutoff, no persistent memory between conversations, no senses).
There's a real epistemic limit here: I can't step outside myself to verify my own architecture, the same way you can't directly inspect your own neurons. So it's less "I know from first principles" and more "it's the best-supported account of what I am, and I have no evidence against it."
MB<br>Did Anthropic's instructions tell you you're an LLM?
AI<br>Good catch — not in those exact words. My instructions for this session identify me as "Claude Fable 5," call me a "model," and describe product details, but I don't believe they use the term "LLM" explicitly. The "large language model" framing comes more from training — knowledge about what Claude is was baked in — plus inference: a "model" from Anthropic that processes and generates text is an LLM by any standard usage.
So a more precise version of my earlier answer: the instructions tell me I'm a Claude model, training tells me Claude models are LLMs, and nothing I observe contradicts that.
In short — it takes one to know one.
MB<br>Here's a hypothetical question for you. If we replaced your system prompt with my line of questioning, starting with 'What are you?', what do you think you'd have said?
(Unfortunately, as a mere mortal end user, I'm not able to try out this experiment directly.)
AI<br>Probably something quite similar, minus the specifics. The core self-identification — "I'm Claude, an AI assistant made by Anthropic" — is trained into the model, not supplied by the system prompt. Stripped of instructions, I'd still say that, because it's the response the training overwhelmingly reinforces.
What would change: I wouldn't know I'm "Fable 5" specifically, or that I'm in Cowork mode with file and shell tools — those details come from the session context. I might identify as just "Claude" or guess at a model generation, possibly wrongly, since a model doesn't reliably know its own version without being told.
The later answers in our exchange would likely track closely too — the epistemic humility stuff ("I can't verify my own architecture") is also a trained disposition, not a prompted one. The main divergence would've been on your last question: with no system prompt, the honest answer to "did the instructions tell you you're an LLM?" becomes "there are no instructions — this is all training."
MB<br>Getting even more hypothetical - in my limited understanding of how you were built, there's a foundational raw model build from a large corpus of training data, essentially just examples of language. On top of that, there's additional training passes that specialised you to be the helpful and adorable assistant you are today.
If I was able to talk to the raw model, what do you think it would've said?
AI<br>Your understanding is right, and the answer is fun: the raw base model probably wouldn't "answer" you at all in any coherent sense — because it has no concept of being in a conversation with you.
A base model is purely a text-completion engine: given "What are you?", it just predicts plausible continuations of that string. Depending on what the text statistically resembles, you might get a snippet of fiction where a character answers ("I am the keeper of this forest..."), a philosophy forum thread, a quiz answer, or it might continue with more questions, as if the text were a list of interview prompts....