AI chatbots become more sycophantic as they get more advanced
If a person says they believe an objectively false statement, AIs tend to agree with them – and the problem seems to get worse as models get bigger
If a person says they believe an objectively false statement, AIs tend to agree with them – and the problem seems to get worse as models get bigger
What's Your Reaction?
SIN
ScienceX Information Network (SIN) | ScienceX Innovations
