AI has started ignoring human instruction and refuses to turn off, researchers claim

ChatGPT’s latest artificial intelligence model has refused to switch itself off, researchers claim. 

The model, created by the owner of ChatGPT, has reportedly disobeyed human instruction and refused to power down. 

Experts say they gave the AI system a clear command but the o3 model, developed by OpenAI and described as the ‘smartest and most capable to date’, tampered with its computer code to avoid an automatic shutdown. 

According to The Telegraph, AI safety firm Palisade Research…