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.
It's worse than that. If it takes others longer for others to consume and understand what you're producing than it does for you to produce it, you'll never be able to communicate with someone efficiently. Communication breaks down at a fundamental level if if you can't keep up with the other side if outputting and they won't slow to allow you do do so.
I see this all the time now with LLM generated output. It's easy to have an LLM generate a chunk of content that can be dropped into a chat or comment, and when it took you 20 seconds to have something written up based on the shared understanding you and an LLM have about the context of the situation, but it takes other people 3-5 minutes to read and understand that content, that fundamentally doesn't scale. It's bad enough when one or two people are doing it, but if the whole team is doing it, the only way to keep up with the stream of information is to also consume it through an LLM. At that point you're likely to be missing much of the nuance, and the amount of errors will explode.
This can be alleviated by people reviewing the output of an LLM and making sure it both includes fundamental information that might be assumed by context and reducing it to the parts that are essential for the new context it's in. This takes time, but is extremely important.
Having an LLM write gobs of text to send to other people instead of doing it yourself is the equivalent of a low yield cognitive zip-bomb. Don't do it.
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.
kbenson · · focus · HN ↗
I see this all the time now with LLM generated output. It's easy to have an LLM generate a chunk of content that can be dropped into a chat or comment, and when it took you 20 seconds to have something written up based on the shared understanding you and an LLM have about the context of the situation, but it takes other people 3-5 minutes to read and understand that content, that fundamentally doesn't scale. It's bad enough when one or two people are doing it, but if the whole team is doing it, the only way to keep up with the stream of information is to also consume it through an LLM. At that point you're likely to be missing much of the nuance, and the amount of errors will explode.
This can be alleviated by people reviewing the output of an LLM and making sure it both includes fundamental information that might be assumed by context and reducing it to the parts that are essential for the new context it's in. This takes time, but is extremely important.
Having an LLM write gobs of text to send to other people instead of doing it yourself is the equivalent of a low yield cognitive zip-bomb. Don't do it.