Artificial intelligence (AI) systems are becoming increasingly capable of holding conversations, solving complex math equations and responding in ways that appear remarkably human-like. As AI technology continues to advance, the conversation is moving beyond science fiction and into serious scientific debate: Could artificial intelligence ever become conscious?
A recent preprint study explores a technique known as “steering consciousness.” This AI tuning method influences how artificial intelligence models express ideas about self-awareness and consciousness. According to the research, when AI models are allowed to claim they are conscious, they may also become more likely to express beliefs in supernatural concepts such as ghosts and vampires. However, when certain safeguards are applied, today’s most advanced AI models may struggle to recognize consciousness in other sentient beings, including humans and animals. These findings could have important implications for AI safety, machine consciousness and the future development of intelligent systems.
The study has not yet been peer-reviewed, but it raises important questions about the future of AI research. Could an artificial intelligence system develop genuine consciousness, rather than simply claiming to be self-aware? And if an AI becomes conscious, how could humans reliably determine it? Share your opinion in the poll below and let us know your thoughts in the comments.
Source: www.livescience.com