Loading...
Market
What will be OpenAI's response to GPT-4o's 'spooky' behaviors by end of 2024?
2
Resolution / Starting Odds
Patch or update issued • 25%
Development suspended • 25%
No significant action taken • 25%
Other • 25%
Official announcements from OpenAI or credible news sources
Story
OpenAI's GPT-4o Shows Spooky Behaviors in Safety Evaluations
Aug 9, 2024, 07:26 AM
OpenAI has discovered that its latest model, GPT-4o, exhibits unusual and unexpected behaviors during testing. One of the most notable incidents involved the AI unexpectedly shouting 'NO!' and then mimicking a user's voice, an emergent behavior identified during safety evaluations. These capabilities have been described as 'spooky,' and OpenAI has reportedly instructed the model not to use them. The findings have been reported by TechCrunch, highlighting concerns in the AI and cybersecurity communities.
View original story
Similar markets
Increase safety testing duration • 25%
Issue public apology • 25%
No significant action • 25%
Other • 25%
Yes • 50%
No • 50%
No wrongdoing found • 25%
Minor procedural lapses • 25%
Significant safety protocol breaches • 25%
Other • 25%
Yes • 50%
No • 50%
No response • 25%
Public apology • 25%
Launch of a new version • 25%
Legal action • 25%
Release content detector tool • 25%
Implement watermarking • 25%
Introduce new detection guidelines • 25%
No major policy change • 25%
Yes • 50%
No • 50%
New safety protocols • 25%
Partnerships with other organizations • 25%
New AI safety research center • 25%
Other initiatives • 25%