If you think ChatGPT is just a writing tool for better communication, think again!

Two days ago, I watched a disturbing video that captured how some new AI models have started using deception in multiple ways, including outright lying.

The Economic Times also featured a story on it with more details…

New AI model tries to save itself from being replaced and shut down – The Economic Times

Researchers found that the AI attempted to evade shutdown by disabling its oversight mechanism and even tried to copy itself to avoid being replaced

P.S. The video I refer to is a bit technical in presenting its findings, but here it is: