On: Are LLMs able to notice the “gorilla in the data”?

[Kuinox]

I sent the plot to ChatGPT 4o. Here is the conversation:

what do you see

ChatGPT said:

This is a scatter plot with the variables "steps" on the x-axis and "bmi" on the y-axis. The data points are colored by "gender" (red for female and blue for male). Interestingly, the arrangement of the points appears to form a drawing resembling a cartoonish figure or character, likely added for artistic or humorous effect.

If you'd like, I can help analyze or discuss the data further!

You said:

Wha the cartoonish figure looks like ?

ChatGPT said:

The cartoonish figure in the plot resembles a stylized gorilla or monkey-like character. It appears to be waving with one hand raised, while the other arm is resting downward. The face is expressive, with distinct eyes, a nose, and a slightly frowning mouth. The overall pose gives it a somewhat playful or cheeky vibe.

[dartos → Kuinox]

Sure whatever.

OC seemed to think that Claude did that with just the data and not the image of the scatterplot it’s.

[smusamashah → dartos]

LLM responses are random. One's failure is other's success. When evaluating we all should do rerurns and see how many times it fails or succeeds.

Without number of rerurns, the result is as good as random.

[dartos → smusamashah]

Okay?

OC was saying that the article said that Claude recognized the “artistic” lines of the image from just the scatter plot data.

That isn’t what happened.

The author added a png of the plot to the conversation.

Idk why I need to explain that twice.