Re:Natural language is the lazy user interface
by zeknife on Saturday January 28, 2023 @08:52AM
(#34557553)
You can avoid post-hoc reasoning by making sure chatgpt works step by step to arrive at the answer instead of first presenting the answer and then the steps. This also makes correct answers more likely, especially if it involves math or some kind of iterative process.
Also: https://skepticink.com/tippling/2013/11/14/post-hoc-rational...
I presume to some extent this is also the case with ChatGPT. I presume this because I don't think most people would understand (or have the time to fully read) the actual process the LLM is using to arrive at a particular output from a particular input.
The end result looks kind of human. But is this the post-hoc human, the bullshitter human, or is this something else entirely (i.e. pattern matching - effectively mimicry, not of the human providing the input, but of the corpus)?