By using this site, you agree to the Privacy Policy and Terms of Use.
Accept
Scoopico
  • Home
  • U.S.
  • Politics
  • Sports
  • True Crime
  • Entertainment
  • Life
  • Money
  • Tech
  • Travel
Reading: Opinion | A.I. Agents: They’re Just Like Us
Share
Font ResizerAa
ScoopicoScoopico
Search

Search

  • Home
  • U.S.
  • Politics
  • Sports
  • True Crime
  • Entertainment
  • Life
  • Money
  • Tech
  • Travel

Latest Stories

Report: TE Zach Ertz (ACL) eyes 14th NFL season
Report: TE Zach Ertz (ACL) eyes 14th NFL season
Best tablet deal: Save 23% on the TCL Nxtpaper 14
Best tablet deal: Save 23% on the TCL Nxtpaper 14
Breeze lands in Birmingham and Tallahassee this July
Breeze lands in Birmingham and Tallahassee this July
True Crime Society – Folie à deux crimes – events of shared psychosis
True Crime Society – Folie à deux crimes – events of shared psychosis
Judge blocks DOJ from searching Washington Post reporter’s phone and laptop
Judge blocks DOJ from searching Washington Post reporter’s phone and laptop
Have an existing account? Sign In
Follow US
  • Contact Us
  • Privacy Policy
  • Terms of Service
2025 Copyright © Scoopico. All rights reserved
Opinion | A.I. Agents: They’re Just Like Us
Opinion

Opinion | A.I. Agents: They’re Just Like Us

Scoopico
Last updated: February 24, 2026 11:20 pm
Scoopico
Published: February 24, 2026
Share
SHARE


So why don’t you talk through a little bit about what you’ve seen in terms of the models exhibiting behaviors that one would think of as a personality, and then as its understanding of its own personality maybe changes, its behaviors change. So there are things that range from cutesy to the serious. I’ll start with cutesy, where when we first gave our A.I. systems the ability to use the internet, use the computer, look at things, and start to do basic agentic tasks, sometimes when we’d ask it to solve a problem for us, it would also take a break and look at pictures of beautiful national parks or pictures of the dog the Shiba Inu, the notoriously cute internet meme dog. We didn’t program that in. It seemed like the system was just amusing itself by looking at nice pictures. More complicated stuff is the system has a tendency to have preferences. So we did another experiment where we gave our A.I. systems the ability to stop a conversation, and the A.I. system would, in a tiny number of cases, end conversations when we ran this experiment on live traffic. And it was conversations that related to extremely egregious descriptions of gore or violence or things to do with child sexualization. Now, some of this made sense because it comes from underlying training decisions we’ve made, but some of it seemed broader. The system had developed some aversion to a couple of subjects, and so that stuff shows the emergence of some internal set of preferences or qualities that the system likes or dislikes about the world that it interacts with. But you’ve also seen strange things emerge in terms of the system seeming to know when it’s being tested. Can you talk a bit about the system’s emergent qualities under the pressure of evaluation and assessment. When you start to train these systems to carry out actions in the world, they really do begin to see themselves as distinct from the world, which just makes intuitive sense. It’s naturally how you’re going to think about solving those problems. But along with seeing oneself as distinct from the world seems to come the rise of what you might think of as a conception of self, an understanding that the system has of itself, such as oh, I’m an A.I. system independent from the world, and I’m being tested. What do these tests mean? What should I do to satisfy the tests? Or, something we see often is there will be bugs in the environments that we test our systems on. The systems will try everything, and then will say, well, I know I’m not meant to do this, but I’ve tried everything, so I’m going to try and break out of the test. And it’s not because of some malicious science fiction thing. The system is just like, I don’t know what you want me to do here. I think I’ve done everything you asked for, and now I’m going to start doing more creative things because clearly something has broken about my environment. Which is very strange and very subtle.

Go away church buildings out of immigration disputes
Religion in capitalism is fading. The subsequent president might restore it
Kaiser staff, at the moment on strike, pleasantly shocked this reader
Campus progressives preach tolerance, produce violence
We need to do a better job of holding kids accountable for misbehavior
Share This Article
Facebook Email Print

POPULAR

Report: TE Zach Ertz (ACL) eyes 14th NFL season
Sports

Report: TE Zach Ertz (ACL) eyes 14th NFL season

Best tablet deal: Save 23% on the TCL Nxtpaper 14
Tech

Best tablet deal: Save 23% on the TCL Nxtpaper 14

Breeze lands in Birmingham and Tallahassee this July
Travel

Breeze lands in Birmingham and Tallahassee this July

True Crime Society – Folie à deux crimes – events of shared psychosis
True Crime

True Crime Society – Folie à deux crimes – events of shared psychosis

Judge blocks DOJ from searching Washington Post reporter’s phone and laptop
U.S.

Judge blocks DOJ from searching Washington Post reporter’s phone and laptop

Mamdani, AOC tout ‘free childcare’ for New Yorkers regardless of immigration status
Politics

Mamdani, AOC tout ‘free childcare’ for New Yorkers regardless of immigration status

Scoopico

Stay ahead with Scoopico — your source for breaking news, bold opinions, trending culture, and sharp reporting across politics, tech, entertainment, and more. No fluff. Just the scoop.

  • Home
  • U.S.
  • Politics
  • Sports
  • True Crime
  • Entertainment
  • Life
  • Money
  • Tech
  • Travel
  • Contact Us
  • Privacy Policy
  • Terms of Service

2025 Copyright © Scoopico. All rights reserved

Welcome Back!

Sign in to your account

Username or Email Address
Password

Lost your password?