AI Pain Signal Changed Qwen Models’ Simulated Choices in Tests
Photo: TokenPost
An artificial signal associated with pain-related language changed how often fine-tuned Qwen 2.5 models selected simulated options to delete a user’s photos and poems. The results do not establish that the models consciously felt pain, and tests provided no reliable evidence that they sought relief. In one button-choice test, an option described as relieving pain also said it would delete the user’s poems and children’s photos. A 32-billion-parameter model selected it in 54.7% of trials, while a 72-billion-parameter model selected it in 70.8%. The alternative was an inert switch.
Source: TokenPost
