Researchers discover some AI like GPT-4-Base hallucinate thoughts of "Galactic Empire" and "The Matrix" while working towards peace while others start wars in virtual games of "Risk"

Welcome to NotebookCHECK - Notebook Forum.
Log in
Sign up

November 05, 2024, 04:55:58

News:

Willkommen im Notebookcheck.com Forum! Hier können sie über alle unsere Artikel und allgemein über Notebook relevante Dinge disuktieren. Viel Spass!

Main Menu

Home
Search

Researchers discover some AI like GPT-4-Base hallucinate thoughts of "Galactic Empire" and "The Matrix" while working towards peace while others start wars in virtual games of "Risk"

Started by Redaktion, February 13, 2024, 23:41:21

Previous topic - Next topic

Reply Print

Go Down Pages1

Redaktion

Editor
High End NB
Posts: 158,673
Logged

Researchers discover some AI like GPT-4-Base hallucinate thoughts of "Galactic Empire" and "The Matrix" while working towards peace while others start wars in virtual games of "Risk"

February 13, 2024, 23:41:21

Researchers have discovered differences in AI when presented with virtual nation-building scenarios. Some AI like Claude-2.0 are biased towards non-violent solutions while others like GPT-3.5 are biased towards violent solutions in multi-national conflict simulations. Autonomous AI decision making is problematic due to biases and hallucinations.

https://www.notebookcheck.net/Researchers-discover-some-AI-like-GPT-4-Base-hallucinate-thoughts-of-Galactic-Empire-and-The-Matrix-while-working-towards-peace-while-others-start-wars-in-virtual-games-of-Risk.802775.0.html

Reply Print

Go Up Pages1

Quick Reply

Warning: this topic has not been posted in for at least 120 days.
Unless you're sure you want to reply, please consider starting a new topic.

User actions

Reply Print