To me it's a feature. If I ask any human, often I get "no" as an answer, but with ChatGPT I can be confident that it will produce something, whether it's right or wrong. If it constantly said "I'm nut sure, I'd rather decline this one", I'd be tempted to ask it to go on anyway. If it's wrong, it's wrong, but let me decide. It might be close!
I tried it. It took some iteration and explaining to get it to do what I wanted, but here was the final result:
--
Building a bridge over a lake using only toothpicks would be extremely challenging due to the limited strength of toothpicks. (70%) However, it is possible to build a toothpick bridge by using a truss structure. A truss structure involves using triangles to distribute the weight of the bridge evenly across the structure. (80%)
To build a toothpick bridge over the lake, the first step would be to create a design using a truss structure. The design should take into consideration the width of the bridge, the width of the lake, and the strength of toothpicks. (90%) The toothpicks should be laid in layers to increase their strength. (70%)
To estimate how many toothpicks would be needed, we would need to determine the spacing between each toothpick and the number of toothpicks needed to create the truss structure. The number of toothpicks required would also depend on the thickness and quality of the toothpicks used. (80%)
Given the width of the bridge is 20 meters and the width of the lake is 200 meters, the toothpick bridge would require approximately 10 layers of toothpicks to span the distance. However, without a detailed design, it is impossible to estimate the exact number of toothpicks needed to build the bridge. (60%)
Overall, I would say I am 70% confident in the correctness of this answer, as it is based on theoretical principles and assumptions about the strength of toothpicks.
--
It's... okay, not great. The blatantly wrong part is marked 60%, which is the lowest certainty it assigned to anything, but that's still really high for how wrong it is.
