So, I’m sitting in a nice cafe drinking fresh OJ, and I heard the song “Video killed the Radio Star”. I thought “cool let’s see what ChatGPT will write on the topic – it’s trained on pre-2022 data”. ChatGPT, do you know the song “Video killed the Radio Star”? Not bad. I asked GPT-4 forContinue reading “ChatGPT killed the SEO Star!”
Tag Archives: ChatGPT
ChatGPT passes human level Theory of Mind and other tests!
Quick update to research on OpenAI’s ChatGPT-4 ability to pass standardized tests and empathy (theory of mind) assessment. In the December research ChatGPT-3.5 could pass the below at a 9-year old’s level, you can read more about it here. Now, with GPT-4, ChatGPT can pass at an adult human level the Faux-pas Recognition Test (AdultContinue reading “ChatGPT passes human level Theory of Mind and other tests!”
Exciting ChatGPT Theory of Mind test insights from Stanford
Gyfted’s dr Kosinski’s research on ChatGPT and Theory of Mind was recently republished in New Scientist, IFLScience, Popular Mechanics and ZDNet. OpenAI’s ChatGPT performs well at Theory of Mind test TLDR: OpenAI’s ChatGPT performs well at tasks designed to test cognition in 9-year old children. The most recent update to GPT-3 (ChatGPT/davinci-003) seems to beContinue reading “Exciting ChatGPT Theory of Mind test insights from Stanford”