←back to thread

I'm absolutely right

(absolutelyright.lol)
648 points yoavfr | 1 comments | | HN request time: 0s | source
Show context
tyushk ◴[] No.45138171[source]
I wonder if this is a tactic that LLM providers use to coerce the model into doing something.

Gemini will often start responses that use the canvas tool with "Of course", which would force the model into going down a line of tokens that end up with attempting to fulfill the user's request. It happens often enough that it seems like it's not being generated by the model, but instead inserted by the backend. Maybe "you're absolutely right" is used the same way?

replies(5): >>45138295 #>>45138496 #>>45138604 #>>45138641 #>>45154548 #
CGamesPlay ◴[] No.45138496[source]
I think this is on the right track, but I think it's a byproduct of the reinforcement learning, rather than something hard-coded. Basically, the model has to train itself to follow the user's instruction, so by starting a response with "You're absolutely right!", it puts the model into the thought pattern of doing whatever the user said.
replies(1): >>45138569 #
1. layer8 ◴[] No.45138569[source]
"Thought pattern" might be overstating it. The fact that "You're absolutely right!" is statistically more likely to precede something consistent with the user's intent than something that isn't, might be enough of an explanation.