Goto

Collaborating Authors

 disobedience


Artificial Intelligent Disobedience: Rethinking the Agency of Our Artificial Teammates

Mirsky, Reuth

arXiv.org Artificial Intelligence

The field of artificial intelligence is currently abuzz with discussions surrounding "agentic AI" or "AI agents." However, despite the widespread excitement, the term agent itself often lacks a precise, universally agreed-upon definition within these conversations. Recently, significant focus has shifted towards agents built upon large language models (LLMs), leveraging some reasoning and language understanding capabilities to execute complex tasks, interact with external tools, and learn from feedback [53, 56, 63, 66, 67]. This move towards more autonomous, goal-directed LLM systems represents a promising yet challenging frontier in AI development. During this time, AI algorithms have also reached superhuman performance in numerous tasks such as game playing [9,57,62,65] and text and image processing [2, 15, 51]. On the other hand, there are still significant obstacles that modern AI has yet to overcome. Grosz [21] proposed a revised Turing Test to create: "A computer team member that can behave, over the long term and in uncertain, dynamic environments, in such a way that people on the team will not notice that it is not human."


Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans?

Zakazov, Ivan, Boronski, Mikolaj, Drudi, Lorenzo, West, Robert

arXiv.org Artificial Intelligence

The ongoing revolution in language modelling has led to various novel applications, some of which rely on the emerging "social abilities" of large language models (LLMs). Already, many turn to the new "cyber friends" for advice during pivotal moments of their lives and trust them with their deepest secrets, implying that accurate shaping of LLMs' "personalities" is paramount. Leveraging the vast diversity of data on which LLMs are pretrained, state-of-the-art approaches prompt them to adopt a particular personality. We ask (i) if personality-prompted models behave (i.e. "make" decisions when presented with a social situation) in line with the ascribed personality, and (ii) if their behavior can be finely controlled. We use classic psychological experiments - the Milgram Experiment and the Ultimatum Game - as social interaction testbeds and apply personality prompting to GPT-3.5/4/4o-mini/4o. Our experiments reveal failure modes of the prompt-based modulation of the models' "behavior", thus challenging the feasibility of personality prompting with today's LLMs.


ICRA Roboethics Challenge 2023: Intelligent Disobedience in an Elderly Care Home

Paster, Sveta, Rogers, Kantwon, Briggs, Gordon, Stone, Peter, Mirsky, Reuth

arXiv.org Artificial Intelligence

With the projected surge in the elderly population, service robots offer a promising avenue to enhance their well-being in elderly care homes. Such robots will encounter complex scenarios which will require them to perform decisions with ethical consequences. In this report, we propose to leverage the Intelligent Disobedience framework in order to give the robot the ability to perform a deliberation process over decisions with potential ethical implications. We list the issues that this framework can assist with, define it formally in the context of the specific elderly care home scenario, and delineate the requirements for implementing an intelligently disobeying robot. We conclude this report with some critical analysis and suggestions for future work.


Alexander Payne stretches himself with 'Downsizing,' but the execution proves puny

Los Angeles Times

Toronto Diary: Ethan Hawke plays a man of the cloth in the haunting'First Reformed' Los Angeles Times critic Justin Chang on the double-Rachel feature (Rachel McAdams and Rachel Weisz) "Disobedience" and how TIFF 2017 has been a showcase of acting talent for the actress leads. Los Angeles Times critic Justin Chang on the double-Rachel feature (Rachel McAdams and Rachel Weisz) "Disobedience" and how TIFF 2017 has been a showcase of acting talent for the actress leads. 'First Reformed,' 'Downsizing' bring climate change to the fore "Will God forgive us for destroying his creation?" The man asking the question is the Rev. Toller (Ethan Hawke), an ex-military chaplain-turned-rural minister who finds himself undergoing a profound crisis of faith. He has already lost a son and a wife, and his insides are rotting from cancer, all of which might well drive even a devout believer to feel that God has abandoned him. But what genuinely haunts Toller, and inspires him to consider an act of extreme, violent desperation, is his eye-opening encounter with Michael (Philip Ettinger), a militant eco-activist who is terrified by the prospect of humanity's mass extinction. "First Reformed," Paul Schrader's somber, beautifully composed and entirely mesmerizing new drama, is not a work of particular subtlety. Its moral argument is as clear and crystalline as its images, shot by cinematographer Alexander Dynan in the nearly square academy-aspect ratio. The severity of Toller's convictions, as well as his disgust at the knowledge that his church has taken money from one of the town's biggest polluters, gives rise to an angry, confrontational question: Why have so many Christians rejected the science of climate change, effectively abdicated their God-given responsibility to look after the Earth?


Sorry, Westworld: We Should Be Able to Torture Robots

#artificialintelligence

Note: This article contains spoilers for the show Westworld. Imagine you find yourself in the middle of the Wild West in the 1850s, a rifle at your side and a sweaty ball of cash in your fist. You strut into a shanty saloon like everything in the world is yours. While you wait for your shot of whiskey, an indescribably attractive dark-haired stranger approaches you. Your significant other is nowhere in sight.