CriticGPT: Finding GPT-4's mistakes with GPT-4

Re:CriticGPT: Finding GPT-4's mistakes with GPT-4 by TeMPOraL on Friday June 28, 2024 @02:47AM (#40818326)

> it's like proposing to stabilize the stack of "turtles all the way down" by adding more turtles

That's completely fine. Say each layer uses the same amount of turtles, but half the size of the layer above. Even allowing for arbitrarily small turtles, the total height of the infinite stack will be just 2x the height of the first layer.

Point being, some series converge to a finite result, including some defined recursively. And in practice, we can usually cut the recursion after first couple steps, as the infinitely long remainder has negligible impact on the final result.

[ Parent | on HN ]

Re:CriticGPT: Finding GPT-4's mistakes with GPT-4 by topherclay on Friday June 28, 2024 @03:21AM (#40818474)

You seem to have interpreted the analogy as meaning "you might run out of turtles" instead of something like: "stacks of turtles aren't stable without stable beneath them, no matter how many turtles you use."

[ Parent | on HN ]

Re:CriticGPT: Finding GPT-4's mistakes with GPT-4 by TeMPOraL on Friday June 28, 2024 @10:43AM (#40821075)

Space them out. I meant that infinite stack of turtles can be stable, of finite height, and for practical purposes, cut off after few layers without noticeable impact on stability.

[ Parent | on HN ]