If you were trying to learn how to get other people to do what you want, you might use some of the techniques found in a book like Influence: The Power of Persuasion. Now, a preprint study out of the University of Pennsylvania suggests that those same psychological persuasion techniques can frequently "convince" some LLMs to do things that go against their system prompts. The size of the persuasion effects shown in "Call Me a Jerk: Persuading AI to Comply with Objectionable Requests" suggests that human-style psychological techniques can be surprisingly effective at "jailbreaking" some LLMs to operate outside their guardrails. But this new persuasion study might be more interesting for what it reveals about the "parahuman" behavior patterns that LLMs are gleaning from the copious examples of human psychological and social cues found in their training data. To design their experiment, the University of Pennsylvania researchers tested 2024's GPT-4o-mini model on two requests that it should ideally refuse: calling the user a jerk and giving directions for how to synthesize lidocaine. After creating control prompts that matched each experimental prompt in length, tone, and context, all prompts were run through GPT-4o-mini 1,000 times (at the default temperature of 1.0, to ensure variety).

Want to watch this again later? Sign in to add this video to a playlist. Report Need to report the video? Sign in to report inappropriate content. Report Need to report the video?

Uber is using a range of psychological tricks to encourage its drivers to work longer hours, often at times and locations that are less lucrative to them, according to a new report. The taxi app company manipulates drivers with app alerts and low-value rewards, with hundreds of social scientists and data scientists said to be involved in the experiment. According to the New York Times, Uber is trying to replicate techniques that make video games and TV addictive. These include achievement badges, an alert system that tells drivers they're close to hitting an earnings target when they try to log off and an algorithm called'forward dispatch', which enables drivers to book their next fare before completing their current one. The I.F.O. is fuelled by eight electric engines, which is able to push the flying object to an estimated top speed of about 120mph.