Computer scientist to develop 'honest' AI that will spot rogue systems and flag 'harmful behaviour'

Non-profit LawZero to create system to act as guardrail against AI agents trying to deceive humans

Scientist AI will 'predict the probability that an agent’s actions will lead to harm' and, if that probability is above a certain threshold, that agent’s proposed action will then be blocked.

An artificial intelligence pioneer has launched a non-profit dedicated to developing an “honest” AI that will spot rogue systems attempting to deceive humans.

Yoshua Bengio, a renowned computer scientist described as one of the “godfathers” of AI, will be president of LawZero, an organisation committed to the safe design of the cutting-edge technology that has sparked a $1tn (€877bn) arms race.