What is the AI alignment problem and how can it be solved?


Share post:

Website of ChatGPT 4 on a smartphone. AI chatbot on OpenAI website. Afyonkarahisar, Turkey - April 3, 2023.; Shutterstock ID 2284532473; purchase_order: -; job: -; client: -; other: -

Shutterstock/Emre Akkoyun

WHAT do paper clips have to do with the end of the world? More than you might think, if you ask researchers trying to make sure that artificial intelligence acts in our interests.

This goes back to 2003, when Nick Bostrom, a philosopher at the University of Oxford, posed a thought experiment. Imagine a superintelligent AI has been set the goal of producing as many paper clips as possible. Bostrom suggested it could quickly decide that killing all humans was pivotal to its mission, both because they might switch it off and because they are full of atoms that could be converted into more paper clips.

The scenario is absurd, of course, but illustrates a troubling problem: AIs don’t “think” like us and, if we aren’t extremely careful about spelling out what we want them to do, they can behave in unexpected and harmful ways. “The system will optimise what you actually specified, but not what you intended,” says Brian Christian, author of The Alignment Problem and a visiting scholar at the University of California, Berkeley.

That problem boils down to the question of how to ensure AIs make decisions in line with human goals and values – whether you are worried about long-term existential risks, like the extinction of humanity, or immediate harms like AI-driven misinformation and bias.

In any case, the challenges of AI alignment are significant, says Christian, due to the inherent difficulties involved in translating fuzzy human desires into the cold, numerical logic of computers. He thinks the most promising solution is to get humans to provide feedback on AI decisions and use this to retrain …

Source link


Please enter your comment!
Please enter your name here

Related articles

Tesla Autopilot arbitration win could set legal benchmark in auto industry

In a victory for Tesla, a California federal judge ruled over the weekend that a group of...

Max Q: Mining moon water

Hello and welcome back to Max Q! In this issue: Mining water on the moon with Starpath Robotics News from...

Republicans still don’t know how to talk to young voters online

In an appeal to younger voters, Republican presidential candidate Vivek Ramaswamy — who proposed raising the voting...

Ousted Flexport CEO Dave Clark strikes back

Dave Clark, the former Amazon executive who was ousted as CEO of Flexport just a year into...