International Organization published research on how chatbots distort reality and their biases toward self-preservation.
Public source
Publisher name
Public post
“Now we learn that when chatbots distort reality, it’s not always because their best efforts at truth have failed. AIs have a bias toward self-preservation. In a well-kn…
Company
International Organization
- Company size
- 501–1,000 employees
Discover more
Similar signals
Similar public activity from other companies.
Research & Knowledge
Brennan Center for Justice
Brennan Center for Justice tested chatbots to see how they respond to election falsehoods and found that they can debunk falsehoods
Research & Knowledge
Advancing Humans with AI
Advancing Humans with AI published a study from the MIT Media Lab following 67 people over four weeks as they judged news headlines and images with an AI chatbot.
Research & Knowledge
Freelance Journalist
Freelance Journalist tested how AI chatbots would handle foreign propaganda according to an NPR report.
Research & Knowledge
The Brookings Institution
The Brookings Institution published a study analyzing how AI-generated text is being corrupted and corrupted by humanizers and autotypers.
Research & Knowledge
ISD (Institute for Strategic Dialogue)