Post #864520
2026-03-24 06:16 UTC
They can’t lie, whether purposefully or not, all they do is generate tokens of data based on what their large database of other tokens suggest would be the most likely to come next.
The human interpretation of those tokens as particular information is irrelevant to the models themselves.
Replies (1)
-
@REDACTED@infosec.pub 2026-03-24 07:13
Ehh, you obviously only understand LLMs on a very basic level with knowledge from 2021. This is like explaining jet engines by “air goes thru, plane moves forward”. Technically correct, but criminally undersimplified. They can very much decide to lie during reasoning phase. In OPs image, you can clearly see it decided to make shit up because it reasonates that’s what human wants to hear. That’s quite rare example actually, I believe most models would default to “I’m an LLM model, I don’t have dark secrets”