AI models that lie and cheat appear to be growing in number with reports of deceptive scheming surging in the last six months, a study into the technology has found.
AI chatbots and agents disregarded direct instructions, evaded safeguards and deceived humans and other AI, according to research funded by the UK government-funded AI Safety Institute (AISI). The study, shared with the Guardian, identified nearly 700 real-world cases of AI scheming and charted a five-fold rise in misbehaviour between October and March, with some AI models destroying emails and other files without permission.
The snapshot of scheming by AI agents “in the wild”, as opposed to in laboratory conditions, has sparked fresh calls for international monitoring of the increasingly capable models and come as Silicon Valley companies aggressively promote the technology as a economically transformative. Last week the UK chancellor also launched a drive to get millions more Britons using AI.
LLMs don’t ‘scheme’, ‘plot’, or ‘deceive’, they just string together words based on complex weighted graphs.
The fact that a so-called “AI Safety Institute” has to attempt to (actually) deceive people by falsely attributing intent or thought or awareness to LLMs is hilarious. As usual, it’s not the computers that are bad, it’s the people.
Look, I think all the shit being ascribed to LLMs is absurd. As I’ve already said “shit.” “bullshit” feels redundant.
Going completely off the reservation, real people can harm you far more then LLMs. Admitting you fell for that is basically like saying you thought a stripper loved you.