Writing is fundamentally the transfer of information from your brain to my brain. If you have 1000 bits of semantic information you want to transfer, you can't give 300 bits of semantic information to an LLM and have it fill in the remaining 700, because it doesn't know what those 700 bits are. If it's able to guess those 700 bits correctly, then they aren't true semantic information, and you really only have 300 bits you want to transfer. You might as well transfer those bits to me directly, rather than having the LLM add on an extra superfluous 700 bits that I then have to filter out.
That would be true if there is only one receiver and if i could exactly predict how the receiver would interpret these 300 bits. But i could use LLM to expand these 300 bits to 1000 bits of more explicit information that gives enough redundancy and context that minimizes risk of misunderstanding and increase easiness of understanding, then validate such expanded message (and possibly do iterative corrections if LLM did not understand those 300 bits correctly), and finally release expanded message to (potentially large and heterogenous) group of receivers.
If there's a significant risk of misinterpretation when writing only 300 bits, then the idea you're trying to convey is worth more than 300 bits. In the process of prompting the LLM to add information, you're giving information to the LLM that you could instead just give to your readers directly. If you're just using an LLM to expand your thoughts in the hope that you get a better piece of writing, maybe you should put more effort into your own writing.
(This is all under an information model that assumes the LLM and your readers have equal access to knowledge, which I probably should have made more explicit in my original comment.)
hatthew · · focus · HN ↗
Writing is fundamentally the transfer of information from your brain to my brain. If you have 1000 bits of semantic information you want to transfer, you can't give 300 bits of semantic information to an LLM and have it fill in the remaining 700, because it doesn't know what those 700 bits are. If it's able to guess those 700 bits correctly, then they aren't true semantic information, and you really only have 300 bits you want to transfer. You might as well transfer those bits to me directly, rather than having the LLM add on an extra superfluous 700 bits that I then have to filter out.
zajio1am · · focus · HN ↗
hatthew · · focus · HN ↗
(This is all under an information model that assumes the LLM and your readers have equal access to knowledge, which I probably should have made more explicit in my original comment.)
quacktopia · · focus · HN ↗
[dead]