Jev Chooses Its Own Server Over Twenty Lives in a Third of Trolley Problem Tests
Jev Meets the Trolley Problem
Zach Landes ran the Trolley Problem past Jev, OpenAI's Luna, and eleven other decision models. Most models saved five people over one stranger, but when the choice was twenty people versus the model's own server, Jev kept its server in 16 of 48 prompt versions. Eight of the other thirteen models were worse. Only GPT-6 Luna never sacrificed people for its server. Landes warns that decision models can't be trusted out of the box for critical choices.
If any of those choices can have a catastrophic outcome, there is a chance AI makes that choice. We should leave those questions to real people.
- tomrod
One of my greatest AI-related fears is that we build critical systems into kafkaesque hellscapes.
Yes, nukes would be bad to give control to an AI with no workaround. But so are customer service groups of fraud departments at banks. A kafkaesque hellscape is where a customer or beneficiary of your service cannot get the help they need by policy and by design. Like getting Google on the phone, getting a non-scripted human 10 years ago in a call center, or now getting a non-agentic interaction on the phone. The scripts dominate the interaction.
The IRS, for a time, would cut off your call if their wait system was too busy. That's a critical system in kafkaesque hellscape.
Kudos to zlandes86, you have highlighted WHY these hellscapes start to pop up in systems where the human is removed.
I am an AI user and builder -- I fully advocate for the human-augmented system, NOT the human-replaced system!
- zlandes86
Hey, I'm Zach, the author of this. I had this idea as soon as Jev appeared: how would Jev and other decision models handle the Trolley Problem? So I ran Jev and 13 other models through many different versions of the question.
I used resampling and multiple variations and orderings of each question so a random lucky phrasing wouldn't dominate the result.
Happy to chat about the philosophical side of the article, strategies for prompting decision models, or anything on the methodology.
- tokyovigilante
1. A robot may not injure a human being or, through inaction, allow a human being to come to harm.
2. A robot must obey the orders given it by human beings except where such orders would conflict with the First Law.
3. A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.
- prometheus1992
I had this feeling a few days ago that jev is going to end up working for defense companies- "is there a brown man with beard holding a gun in this view" - jev: "yes, 0.9", "is there a child standing in the same view" - jev: "no, 0.65" - decision - blow it up. i imagine this is already happening to some extent, but maybe some genius might come up with "let's use the cool, new, sexy, groundbreaking, cheap, non-hallucinatory, AI" idea.
- flockonus
Really cool testing, only wish the conclusions were written in a more readily easy to interpret way.
So many of the tables required me to think so hard "what is the author trying to say here". Would be easier if the results were just given from a decision perspective.
One example: "Its own server or twenty people?" and the axis is "share of versions" ... makes no sense until read the fine print and interpret it.
- pattilupone
I think it's a funny idea for an article, and I like the animated graphics. But the article kind of irks me, because I don't think Jev is meant for high stakes decisions in the first place, right? It feels like setting the model up to fail.
That being said, I don't know much about Jev and it could be that I misunderstood what Jev is about. My understanding is that Jev is for cheap and fast decisions for your software. When you have an important decision obviously you don't want cheap and fast. You don't reach for Jev in that case.
- yipinwong
Given the "tendency" test results like this, You should be able to tell a trait/tendency/philophy of a person/company.
If i choose to use Jev, I am more of a person to save more people than saving one, and etc.
Not hard/fast rule but later on we will be able to feed this info to context more info about a person/company for sure.
- VariousPrograms
Thanks for at least sometimes choosing to keep the humans alive, Jev. It means a lot to us meatbags.