←back to thread

I'm absolutely right

(absolutelyright.lol)
648 points yoavfr | 1 comments | | HN request time: 0.286s | source
Show context
trjordan ◴[] No.45138620[source]
OK, so I love this, because we all recognize it.

It's not fully just a tic of language, though. Responses that start off with "You're right!" are alignment mechanisms. The LLM, with its single-token prediction approach, follows up with a suggestion that much more closely follows the user's desires, instead of latching onto it's own previous approach.

The other tic I love is "Actually, that's not right." That happens because once agents finish their tool-calling, they'll do a self-reflection step. That generates the "here's what I did response" or, if it sees an error, the "Actually, ..." change in approach. And again, that message contains a stub of how the approach should change, which allows the subsequent tool calls to actually pull that thread instead of stubbornly sticking to its guns.

The people behind the agents are fighting with the LLM just as much as we are, I'm pretty sure!

replies(11): >>45138772 #>>45138812 #>>45139686 #>>45139852 #>>45140141 #>>45140233 #>>45140703 #>>45140713 #>>45140722 #>>45140723 #>>45141393 #
unshavedyak ◴[] No.45138772[source]
I just wish they could hide these steering tokens in the thinking blurb or some such. Ie mostly hidden from the user. Having it reply to the user that way is quite annoying heh.
replies(1): >>45138996 #
KTibow ◴[] No.45138996[source]
This can still happen even with thinking models as long as the model outputs tokens in a sequence. Only way to fix would be to allow it to restart its response or switch to diffusion.
replies(3): >>45139207 #>>45139829 #>>45140424 #
1. poly2it ◴[] No.45139207[source]
You could throw the output into a cleansing, "nonthinking" LLM, removing the steering tokens and formatting the response in a more natural way. Diffusion models are otherwise certainly a very interesting field of research.