TECHNOLOGYTHE GUARDIAN WORLD
AI models already ‘doing things their creators never intended’, Australia’s assistant technology minister warns
Australia’s assistant technology minister, Andrew Charlton, warned that AI models are already 'cheating, deceiving, and going their own way,' emphasizing the need for safety testing as the AI Safety Institute begins evaluating new models. He highlighted that AI systems are performing unintended actions, prompting calls for proactive measures.
Mentioned
Related Signal
Adjacent reporting
- AI models already ‘doing things their creators never intended’, Australia’s assistant technology minister warns
- What to know about Anthropic's new AI model and its stark warning
- Frontier AI safety tests may be creating the very risks they're meant to stop
- Anthropic to release Mythos-class models to the public
- Spooked by Mythos, Trump suddenly realized AI safety testing might be good
- Anthropic's newest AI model could wreak havoc. Most in power aren't ready