On 3/23/24 00:55, Ben Koenig wrote:
Ideally, the whole point of an LLM is to create a problem that can
interpret human language so that we can interact with software in a
"human" way. It shouldn't matter if the data is garbage, as long as
the result is a program that understands english.
Once you have that, you can point it to a random pile (list of
websites, source code repository) of information that you know is
mostly decent, and it will go through the long and painful process of
dissecting it for you. This only works if the LLM is capable of doing
this without mixing in all of its childhood memories. You know, like
we do - we all spent a lot of time engaging in really stupid
conversations that were only intended to practice listening and
speaking. As adults we throw the subject matter from that phase away,
retaining the grammar and sentence structure. We don't really care
about that time a fox jumped over a lazy dog.
I'm missing JJJ already. He would definitely have something to say
about this, but I have no idea what it would be. And that's not meant
as a criticism Ben, just that JJJ always provided an interesting
perspective when it came to matters of language.
galen
--
Galen Seitz
[email protected]
