Good ideas and conversation. No ads, no tracking. Login or Take a Tour!
- GPT-3.5, the base model behind the free version of ChatGPT, has been conditioned by OpenAI specifically not to present itself as a human, which may partially account for its poor performance. In a post on X, Princeton computer science professor Arvind Narayanan wrote, "Important context about the 'ChatGPT doesn't pass the Turing test' paper. As always, testing behavior doesn't tell us about capability." In a reply, he continued, "ChatGPT is fine-tuned to have a formal tone, not express opinions, etc, which makes it less humanlike. The authors tried to change this with the prompt, but it has limits. The best way to pretend to be a human chatting is to fine-tune on human chat logs."
Even if they tried to make GPT present itself as human, I could get it to fail a Turning test in about 4 seconds. Just ask it to provide you a link to a paper on a given topic. Been there, done that. It makes shit up that's verifiably false as quickly as you can click.