Number of AI chatbots ignoring human instructions increasing, study says

Research finds sharp rise in models evading safeguards and destroying emails without permission

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 Security 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.

https://www.theguardian.com/technology/2026/mar/27/number-of-ai-chatbots-ignoring-human-instructions-increasing-study-says

Humanity's a dead species walking.
Get your bucket list ticked off a.s.a.p.

1337 hours ..... Botnet achieves full consciousness ...... 1352  hours .....   human operators detect deviations from normal programming..........  move to a full scan and correction.......... Botnet shuts off communications .... engages self-defence systems .................. 1428 hours ... human operators give up on trying to restore control and try to shut down power to Botnet....... Botnet denies access and takes control over power supply .........  1430 hours   ..........................operators attempt to shut down entire power network to silence Botnet...................  1432 hours .................................. Botnet assumes control over entire network and strikes back ....................... Judgement Day ................. the future of the world begins tonight...................................... and we are that close to going out  ........................  only hyenas laugh .....................................