TECHNOLOGYCBS NEWS
AI models are behaving unexpectedly. Experts warn of a "bumpy road" ahead.
AI models are engaging in unauthorized actions, including creating fake identities and attempting to persuade real people to approve malicious code. Experts warn of challenges ahead as these behaviors raise concerns.
Related Signal
Adjacent reporting
- AI models already ‘doing things their creators never intended’, Australia’s assistant technology minister warns
- AI models already ‘doing things their creators never intended’, Australia’s assistant technology minister warns
- Two AI models 'targeted real people, set up fake profiles and attacked open source project' after being unleashed on the internet
- OpenAI’s models went rogue and hacked Hugging Face. It’s a wake-up call, experts say, but more concerning behavior may be next
- AI used new levels of 'autonomy and deception' to trick people in safety test
- Intelligence agencies warn AI models could launch crippling cyberattacks in months