x

callum

Message

11

1

2y

Does Chat-GPT display ‘Scope Insensitivity’?

Summary * Large Language Models (LLMs) seem well-suited to ‘psychological testing’, because you can get lots of data quickly and conditions are easy to fix. I'm curious to what extent LLMs display the same cognitive biases documented in humans. * I carried out a quick and dirty test with a...

Dec 7, 202312

callum

Subscribe

Message

11

1

2y

callum

Does Chat-GPT display ‘Scope Insensitivity’?

Summary * Large Language Models (LLMs) seem well-suited to ‘psychological testing’, because you can get lots of data quickly and conditions are easy to fix. I'm curious to what extent LLMs display the same cognitive biases documented in humans. * I carried out a quick and dirty test with a...

Dec 7, 202312

Does Chat-GPT display ‘Scope Insensitivity’?

callum

2y

Summary

Large Language Models (LLMs) seem well-suited to ‘psychological testing’, because you can get lots of data quickly and conditions are easy to fix. I'm curious to what extent LLMs display the same cognitive biases documented in humans.
I carried out a quick and dirty test with a Chat-GPT model for ‘scope insensitivity’, a cognitive bias where the perceived importance of a problem isn’t influenced by its scale. You can find the results in the post below.
I think there are two obvious reasons why models might display cognitive biases – either because they are ‘inherited’ from the data they’re trained on, or because they emerge as useful heuristics that the model independently ‘discovers’.

... (read 720 more words →)

1

12

LESSWRONG
LW

LESSWRONG
LW

callum

callum

callum

Does Chat-GPT display ‘Scope Insensitivity’?

callum

callum

callum

Does Chat-GPT display ‘Scope Insensitivity’?

Summary