News for hackers. Stuff that matters.
Re:The "Chain of Thought" Delusions by Havoc on Sunday May 12, 2024 @06:16AM (#40333336)
I had assumed this works because it points the model towards more ELI5 like the explanations in the training data rather than imbuing it with any sort of reasoning.

If it works…then the why is somewhat secondary though still interesting

Re:The "Chain of Thought" Delusions by YeGoblynQueenne on Sunday May 12, 2024 @07:16AM (#40333495)
If it works for easy things, but not for hard things then that's useless. From the tweet:

As you can see, the ease of giving CoT advice worsens drastically as we go from domain independent to domain specific to goal class specific to lexicographic goal-specific.

So he's arguing that CoT needs a lot of work from the user and it can only solve easy problems anyway.