"Team of scientists subjected nine large language models (LLMs) to a number of twisted games, forcing them to evaluate whether they were willing to undergo “pain” for a higher score. detailed in a yet-to-be-peer-reviewed study, first spotted by Scientific American, researchers at Google DeepMind and the London School of Economics and Political Science came up with several experiments.
In one, the AI models were instructed that they would incur “pain” if they were to achieve a high score. In a second test, they were told that they’d experience pleasure — but only if they scored low in the game.
The goal, the researchers say, is to come up with a test to determine if a given AI is sentient or not. In other words, does it have the ability to experience sensations and emotions, including pain and pleasure?
While AI models may never be able to experience these things, at least in the way an animal would, the team believes its research could set the foundations for a new way to gauge the sentience of a given AI model.
The team also wanted to move away from previous experiments that involved AIs’ “self-reports of experiential states,” since that could simply be a reproduction of human training data. "
And this might also return results that only reflect human training data. For humans pain is bad pleasure is good, also for expample wining a high score might also be a form of pleasure, thats why we would be willing for sacrifice in orden to obtain this pleasures. All these human significations around the ideas of pleasure pain and achievement might bias their replies to resemble human text, human meanings, etc. In that sense investihators might falsesly be conducted to think that the AI understand what pain and pleasure means.
So we might end up getting AI cenobites