Comment by ec109685

GPT also fails at this:

> Which weighs more a pound of feathers or a pound of feathers

< A pound of feathers and a pound of bricks weigh the same. Both are one pound. The difference lies in volume and density: feathers take up more space and are less dense, while bricks are denser and take up less space.

Bard does better but still doesn't "get" it:

< Neither! Both a pound of feathers and a pound of feathers weigh the same, which is exactly one pound. In other words, they have the same mass.

< This is a classic riddle that plays on our expectations and assumptions. We often associate weight with density, so we might initially think that feathers, being lighter and fluffier than other materials, would weigh less than something more compact like metal. However, as long as both piles of feathers are measured to be exactly one pound, they will weigh the same.

At least it recognizes its limitations:

> My reason for mentioning other materials was likely due to my training data, which contains a vast amount of information on various topics, including the concept of weight and density. As a large language model, I sometimes tend to draw on this information even when it is not directly relevant to the current task. In this case, I made the mistake of assuming that comparing feathers to another material would help clarify the point, but it only served to complicate the matter.

For ChatGPT if you ask it to solve it step by step, it does better: https://chat.openai.com/share/7810e5a6-d381-48c3-9373-602c14...