AI can pass the Turing Test in live chats and appear more human than us. I am spooked now
A recent study from UC San Diego reveals that AI can successfully pass the Turing Test in live chat scenarios. The study found that GPT-4.5 was able to convince judges that it was a human participant during real-time conversations. This development raises concerns about the implications of AI's increasing ability to mimic human behavior.
- ▪AI has demonstrated the ability to pass the Turing Test in live chat settings.
- ▪In a study, GPT-4.5 outperformed human participants in convincing judges of its humanity.
- ▪Judges based their evaluations on real-time conversations rather than static prompts.
Opening excerpt (first ~120 words) tap to expand
AI can pass the Turing Test in live chats, and the latest result lands with a chill. In a UC San Diego study, GPT-4.5 outperformed real participants at convincing judges there was a person on the other side. The setup was harder to shrug off than a standard benchmark. Judges reacted to real-time exchanges rather than static prompts, then made a fast call based on conversation alone. Recommended Videos (function(){let containerEl=document.getElementById('dt-cnx-container-6a0daa3171221');const deletePlayer=()=>{if(containerEl){containerEl.remove();containerEl=null}};if(!window.DT_RELATED_PLAYER_PROVIDER){deletePlayer();return} const iasAnId=decodeURIComponent('927851');if(!window.dtCNXReady){const loadIAS=()=>{return new Promise((resolve)=>{const…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Digital Trends.