Right now, Logseq just commits with "Auto saved by Logseq" as the commit message. It could be an interesting opportunity to leverage a large language model like GPT to make these more descriptive.
Personally, I actually have some pretty large reservations about doing it, because it would mean posting potentially private journal content to a black box server in the cloud. But, it's still a very interesting idea, that could maybe be replaced with self-hostable large language models in the future.
What do you think?
I have no idea if this is even possible with the Logseq plugin API, but presumably the default git commit feature could be turned off in favour of a custom one anyway.
Right now, Logseq just commits with "Auto saved by Logseq" as the commit message. It could be an interesting opportunity to leverage a large language model like GPT to make these more descriptive.
Personally, I actually have some pretty large reservations about doing it, because it would mean posting potentially private journal content to a black box server in the cloud. But, it's still a very interesting idea, that could maybe be replaced with self-hostable large language models in the future.
What do you think?
I have no idea if this is even possible with the Logseq plugin API, but presumably the default git commit feature could be turned off in favour of a custom one anyway.