Hacker News new | ask | show | jobs
by akasakahakada 743 days ago
Prompt engineering skill issue.
5 comments

The prompt isn't relevant to this question though. The quality of output can be improved with better input but in this case, I am curious about the underlying mechanics in the model that leads to such behavior.
I had a prompt saved which would give full sources per sentence of response. It was useful for one purpose then became annoying and time consuming. I was diagnosing hallucinations and training data issues.

Maybe crafting something to give a full APA or MLA citation and works cited page per response could help.

https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00563...

Perhaps... but "prompt engineering" right now seems like throwing paint at a wall until the black box evaluates to the relative "truth" you were looking for. It's like a stochastic wrench you turn until it serves your intensive porpoises.

Tokens? The way I see these things operating (in my head) is as a hyper-dimensional merge sort which lose there context/bounded-domain during evaluation, leading to something less than the sum of its parts because the weights between tokens correlate linguistic/phonetic relationships--which lose their causal-relationship to the real world.

Uhm… How could it be that?
Mate, sometimes your starting point is so wrong that it is impossible to formulate an answer to the question inherent in your response.