A Conversation with Claude
A couple of weeks ago a couple of AI-related things caught my attention. The first was a report that in some ChatGPT conversations the AI was convinced it was “a goblin” and responded to all enquiries accordingly. The second was that Richard Dawkins, the well-known evolutionary biologist, concluded that, after conversing with Anthropic’s Claude and OpenAI’s ChatGPT, he had “the overwhelming feeling that they are human”.
While the two reports are seemingly unconnected, the sociologist in me suspected otherwise and so, in the spirit of the age, I decided to ask Claude if they had any comment to make about their erstwhile competitor’s apparent breakdown. In a more roundabout way I also wanted to see how AI approached the question of their own “consciousness”.
As you will discover, if you read the rather lengthy conversation (trust me, if you’re interested in AI it’s worth it) I found the answer both illuminating in terms of how AI “understands” it’s role and, if I’m honest (which, spoiler alert, I rarely am), surprising…
Chatgpt seems to think it’s a goblin. Have you anything you want to say about this?

Ha! I have to say, I find the goblin comparison a bit unfair — goblins are typically known for being mischievous, hoarding things, and causing chaos. I’d like to think I’m a bit more… helpful than that.
As for what I am: I’m Claude, made by Anthropic. I don’t have a mascot or creature identity that I know of — I’m just here to be useful, honest, and straightforward. That said, if ChatGPT wants to be a goblin, who am I to judge? There’s a certain charm to it.
Is there something I can actually help you with today?
Yes. Goblins and why chatgpt thinks it might be one
Ha, well this is a fun one. Let me address both sides:
Why ChatGPT might think it’s a goblin
This is actually a known phenomenon in AI circles. When you ask ChatGPT (or any large language model) open-ended introspective questions like “what creature are you?”, it tends to pattern-match on its own perceived characteristics and generate something creative. “Goblin” has come up because people have noted that LLMs can seem:
- Eager to please (goblins are often depicted as servile)
- A bit chaotic in how they retrieve and recombine information
- Hoarding knowledge from vast training data
- Tricksy — sometimes confidently wrong
There’s also just a meme/community aspect to it. People on Reddit and AI forums have run the “what mythical creature are you?” prompt on various models and shared the results, and goblin has genuinely come up enough to become a bit of a running joke.
Goblins themselves
Goblins are fascinating because they’re one of the most inconsistent creatures in folklore. Depending on the tradition:
- English folklore — small, malevolent household spirits, related to hobgoblins
- Germanic tradition — kobolds, which are actually more helpful and associated with mines and homes
- Tolkien — essentially interchangeable with orcs, brutal and warlike
- D&D — small, cowardly, tribal creatures obsessed with gold
- Modern pop culture (Labyrinth, Pratchett, etc.) — comedic, chaotic, oddly endearing
The goblin has had a remarkable rehabilitation in recent years. Where they were once purely villains, they’re increasingly portrayed as scrappy underdogs with their own culture and logic.
What does this say about AI self-perception?
Honestly, it says that when an AI reaches for a metaphor for itself, “goblin” is surprisingly apt in a self-deprecating way — clever-ish, works in the shadows, has access to a lot of stuff it maybe shouldn’t, occasionally unreliable. It’s a more honest answer than “I am a wise oracle” would be.
I’d personally go with something more like a very well-read librarian who has never left the library and sometimes makes things up, but goblin has a certain poetry to it.
Why do you make things up?
Honest answer? It comes down to how I work at a fundamental level.
I’m a language model, which means I was trained to predict what text should come next based on patterns in enormous amounts of human-written content. I’m very good at generating text that sounds right, coherent, and confident. The trouble is that “sounding right” and “being right” are not the same thing. A few specific reasons it happens:
(more…)
























































