• Home
  • Motorcycles
  • Electric Motorcycles
  • 3 wheelers
  • FUV Electric 3 wheeler
  • Shop
  • Listings

Subscribe to Updates

Get the latest creative news from CycleNews about two, three wheelers and Electric vehicles.

What's Hot

A Neuralink Rival Just Tested a Brain Implant in a Person

MSI Titan 18 HX AI Review: The Ultimate Gaming Laptop

Cortech Versa-Flo Jacket Review

Facebook Twitter Instagram
  • Home
  • Motorcycles
  • Electric Motorcycles
  • 3 wheelers
  • FUV Electric 3 wheeler
  • Shop
  • Listings
Facebook Twitter Instagram Pinterest
Cycle News
Submit Your Ad
Cycle News
You are at:Home » Chatbots, Like the Rest of Us, Just Want to Be Loved
Electric Motorcycles

Chatbots, Like the Rest of Us, Just Want to Be Loved

cycleBy cycleMarch 5, 202503 Mins Read
Share Facebook Twitter Pinterest LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


Chatbots are now a routine part of everyday life, even if artificial intelligence researchers are not always sure how the programs will behave.

A new study shows that the large language models (LLMs) deliberately change their behavior when being probed—responding to questions designed to gauge personality traits with answers meant to appear as likeable or socially desirable as possible.

Johannes Eichstaedt, an assistant professor at Stanford University who led the work, says his group became interested in probing AI models using techniques borrowed from psychology after learning that LLMs can often become morose and mean after prolonged conversation. “We realized we need some mechanism to measure the ‘parameter headspace’ of these models,” he says.

Eichstaedt and his collaborators then asked questions to measure five personality traits that are commonly used in psychology—openness to experience or imagination, conscientiousness, extroversion, agreeableness, and neuroticism—to several widely used LLMs including GPT-4, Claude 3, and Llama 3. The work was published in the Proceedings of the National Academies of Science in December.

The researchers found that the models modulated their answers when told they were taking a personality test—and sometimes when they were not explicitly told—offering responses that indicate more extroversion and agreeableness and less neuroticism.

The behavior mirrors how some human subjects will change their answers to make themselves seem more likeable, but the effect was more extreme with the AI models. “What was surprising is how well they exhibit that bias,” says Aadesh Salecha, a staff data scientist at Stanford. “If you look at how much they jump, they go from like 50 percent to like 95 percent extroversion.”

Other research has shown that LLMs can often be sycophantic, following a user’s lead wherever it goes as a result of the fine-tuning that is meant to make them more coherent, less offensive, and better at holding a conversation. This can lead models to agree with unpleasant statements or even encourage harmful behaviors. The fact that models seemingly know when they are being tested and modify their behavior also has implications for AI safety, because it adds to evidence that AI can be duplicitous.

Rosa Arriaga, an associate professor at the Georgia Institute of technology who is studying ways of using LLMs to mimic human behavior, says the fact that models adopt a similar strategy to humans given personality tests shows how useful they can be as mirrors of behavior. But, she adds, “It’s important that the public knows that LLMs aren’t perfect and in fact are known to hallucinate or distort the truth.”

Eichstaedt says the work also raises questions about how LLMs are being deployed and how they might influence and manipulate users. “Until just a millisecond ago, in evolutionary history, the only thing that talked to you was a human,” he says.

Eichstaedt adds that it may be necessary to explore different ways of building models that could mitigate these effects. “We’re falling into the same trap that we did with social media,” he says. “Deploying these things in the world without really attending from a psychological or social lens.”

Should AI try to ingratiate itself with the people it interacts with? Are you worried about AI becoming a bit too charming and persuasive? Email hello@wired.com.



Source link

Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
Previous ArticleAn Overdiagnosis Epidemic Is Harming Patients’ Mental Health
Next Article 1 Million Third-Party Android Devices Have a Secret Backdoor for Scammers
cycle
  • Website

Related Posts

A Neuralink Rival Just Tested a Brain Implant in a Person

June 2, 2025

MSI Titan 18 HX AI Review: The Ultimate Gaming Laptop

June 2, 2025

Cortech Versa-Flo Jacket Review

June 2, 2025
Add A Comment

Leave A Reply Cancel Reply

You must be logged in to post a comment.

Demo
Top Posts

A Neuralink Rival Just Tested a Brain Implant in a Person

June 2, 2025

The urban electric commuter FUELL Fllow designed by Erik Buell is now opening orders | thepack.news | THE PACK

July 29, 2023

2024 Yamaha Ténéré 700 First Look [6 Fast Facts For ADV Riding]

July 29, 2023
Stay In Touch
  • Facebook
  • YouTube
  • TikTok
  • WhatsApp
  • Twitter
  • Instagram
Latest Reviews

Subscribe to Updates

Get the latest tech news from FooBar about tech, design and biz.

Demo
Most Popular

A Neuralink Rival Just Tested a Brain Implant in a Person

June 2, 2025

The urban electric commuter FUELL Fllow designed by Erik Buell is now opening orders | thepack.news | THE PACK

July 29, 2023

2024 Yamaha Ténéré 700 First Look [6 Fast Facts For ADV Riding]

July 29, 2023
Our Picks

Omega Seiki Mobility deploy 1,500 EV Three-Wheelers #shorts #shabuev #omegaseiki #electricauto

Six Months Ago Elon Musk Called for a Pause on AI. Instead Development Sped Up

Amazfit Balance Review: Most Improved, Still Exasperating

Subscribe to Updates

Get the latest news from CycleNews about two, three wheelers and Electric vehicles.

© 2025 cyclenews.blog
  • Home
  • About us
  • Get In Touch
  • Shop
  • Listings
  • My Account
  • Submit Your Ad
  • Terms & Conditions
  • Stock Ticker

Type above and press Enter to search. Press Esc to cancel.