

2·
2 years agoBut if we know that it makes things up and gets things wrong, how can we trust any information it gives us? Fact-checking is one thing, but at that point, you might as well skip the LLM and just look the information up yourself.
But if we know that it makes things up and gets things wrong, how can we trust any information it gives us? Fact-checking is one thing, but at that point, you might as well skip the LLM and just look the information up yourself.
My question to you: how do you solve the moderation staffing requirements? Imagine if every post that got downvoted was instead reported.
The solution here assumes that ‘report’ sends a post to some nether realm where nobody has to deal with it ever again; but all it’s doing is passing the buck, and I don’t think that’s viable unless the moderation team is the same size as the userbase.
If you then mandate a sixty-character comment, then nobody’s going to bother reporting anyway, and you end up with a worse problem…