Thank you for introducing me to new insights regarding nondeterminism, interpretability, and fluidity. We have inputs and outputs but we don’t quite know all that is going on in the middle. That is an intriguing engineering challenge to solve. Citing the source is pretty much the only way the user can assess the veracity of the information we are given. Moreover, not providing citations and links that point to original source material seems intellectually dishonest if not predatory. That seems a technical problem worth solving.
It looks like there’s interesting research being done at Princeton (“Enabling Large Language Models to Generate Text with Citations”).The cited papers also seem worth a read.
Thank you for introducing me to new insights regarding nondeterminism, interpretability, and fluidity. We have inputs and outputs but we don’t quite know all that is going on in the middle. That is an intriguing engineering challenge to solve. Citing the source is pretty much the only way the user can assess the veracity of the information we are given. Moreover, not providing citations and links that point to original source material seems intellectually dishonest if not predatory. That seems a technical problem worth solving.
There are some workarounds for providing sources but it is a super interesting challenge that many people are working on.
It looks like there’s interesting research being done at Princeton (“Enabling Large Language Models to Generate Text with Citations”).The cited papers also seem worth a read.
I'll check it out. Thanks for bringing it to my attention.