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.
I don’t quite think this tracks. Perhaps you want to communicate 1000 bits that are well known and can be referenced with a 300 bit key. Then the LLM can easily retrieve the remaining information. It’s like sending someone a link to the Wikipedia page instead of explaining something yourself.
No, I don’t want to read LLM writing because it is BAD at it. It doesn’t really understand how humans think (because it thinks differently), and doesn’t seem to understand core principles very well (presumably due to the lack of world model), so it can’t write something humans enjoy yet.
That's kind of my point. If the 1000 bits are well known, then their inclusion isn't new semantic information. By pasting an LLM's output, you're deciding for your reader that they don't already know that information, and deciding that your LLM prompt is better than whatever they would to to obtain that information if they lack it. IMO, it's much better to give your readers the 300-bit key, and let them decide for themselves if they want/need to get more information, and if so, how.
Why not do both though? I often now write my human summary, then paste in also the content you could get by asking a bot (with markers for which is which). You’re perfectly welcome to ignore the bot text, or ask your own bot, but bots are pretty slow, so I also don’t want to wait for it to “decompress” that 300 bit blob to get the detailed page back. But my human summaries are also only intended to be 50 bits — compressed again to just pass the signal I mean to convey, and not the whole prompt needed to fetch the right info from the right place to substantiate the claim.
TLDR the length was the same curtesy of tl;dr before, just now with a different name.
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.
TwelveEyes · · focus · HN ↗
No, I don’t want to read LLM writing because it is BAD at it. It doesn’t really understand how humans think (because it thinks differently), and doesn’t seem to understand core principles very well (presumably due to the lack of world model), so it can’t write something humans enjoy yet.
hatthew · · focus · HN ↗
manwe150 · · focus · HN ↗
TLDR the length was the same curtesy of tl;dr before, just now with a different name.