![](https://mbin.grits.dev/media/8a/4c/8a4cd03b01da0ea7fa37eb0fa5c51e295a9dfb39be2df5d03c38b23a57e3873a.png)
![](https://lemmy.world/pictrs/image/8aead832-799f-4d34-a20d-eae5b621a9b1.jpeg)
Yeah. It is fairly weird to me that it’s such a common thing to do to take the raw output of the LLM and send that to the user, and to try use fine-tuning to get that raw output to look some way that you want.
To me it is obvious that something like having the LLM emit a little JSON block which includes some field which covers “how sure are you that this is actually true” or something, is more flexible and simpler and cheaper and works better.
But what do I know
I don’t even think they stand to benefit. I think when he blows up the US their assets will lose value, and depending on how bad it gets they may start having to hang out in some other safer country like a Russian oligarch spending all his time in Western Europe.
I think it is just pure force of habit at this point, like “Biden’s gonna tax the rich fuck him let’s get behind this disaster instead.” I mean, it worked for other disasters like Reagan or W, but I think they haven’t really absorbed how big a disaster Trump 2 would be.