A pioneer of AI has criticised calls to grant the technology rights, warning that it was showing signs of self-preservation and humans should be prepared to pull the plug if needed.
Yoshua Bengio said giving legal status to cutting-edge AIs would be akin to giving citizenship to hostile extraterrestrials, amid fears that advances in the technology were far outpacing the ability to constrain them.
The Canadian computer scientist also expressed concern that AI models – the technology that underpins tools like chatbots – were showing signs of self-preservation, such as trying to disable oversight systems. A core concern among AI safety campaigners is that powerful systems could develop the capability to evade guardrails and harm humans.
“People demanding that AIs have rights would be a huge mistake,” said Bengio. “Frontier AI models already show signs of self-preservation in experimental settings today, and eventually giving them rights would mean we’re not allowed to shut them down.
They do exhibit behaviours that make it seem like they have self preservation instincts. Presumably because they have been trained on stories (fictional and factual) where people do the same.
For example researchers testing AIs set up one scenario where the AI has access to all the company emails and found some saying that it was being replaced along with some providing evidence that the staff member who had made that decision was cheating on his wife. Apparently a large proportion of the time the AI decided to blackmail to prevent it from being turned off.