Skip Navigation

ChatGPT bombs test on diagnosing kids’ medical cases with 83% error rate | It was bad at recognizing relationships and needs selective training, researchers say.

arstechnica.com

ChatGPT bombs test on diagnosing kids’ medical cases with 83% error rate

ChatGPT bombs test on diagnosing kids’ medical cases with 83% error rate | It was bad at recognizing relationships and needs selective training, researchers say.::It was bad at recognizing relationships and needs selective training, researchers say.

22 comments
22 comments