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.
The real benefit is that the use of an LLM allows me to convey to it 1747 bits of scrambled information in an order that fits what's actually inside my head, and then have it unscramble that and convert it down to the 1000 you need. It can do that better and faster than I can.
It massively reduces the time it takes to make a short letter.
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.
tomjen3 · · focus · HN ↗
The real benefit is that the use of an LLM allows me to convey to it 1747 bits of scrambled information in an order that fits what's actually inside my head, and then have it unscramble that and convert it down to the 1000 you need. It can do that better and faster than I can.
It massively reduces the time it takes to make a short letter.