KPMG pulls report on AI usage due to apparent hallucinations
1–10 of 37 posts
Re: KPMG pulls report on AI usage due to apparent hallucinations
#2Re: KPMG pulls report on AI usage due to apparent hallucinations
#3Re: KPMG pulls report on AI usage due to apparent hallucinations
#4[dupe] https://news.ycombinator.com/item?id=48515733
Re: KPMG pulls report on AI usage due to apparent hallucinations
#5Re: KPMG pulls report on AI usage due to apparent hallucinations
#6Re: KPMG pulls report on AI usage due to apparent hallucinations
#7Well they were true to their word about demonstrating a new and increasingly relevant definition of "excellence."
Re: KPMG pulls report on AI usage due to apparent hallucinations
#8I use this regularly for my personal financial research system. Even flagship models make mistakes. Though currently the issue is usually the model using a figure from and older report. Cross-check reduces that dramatically.
Re: KPMG pulls report on AI usage due to apparent hallucinations
#9The crazy thing is the level of effort to say, "have a sub agent validate all references and figures" is so low. I'm paraphrasing, but you don't need much more than that. It would have prevented 99% of the face palms. I use this regularly for my personal financial research system. Even flagship models make mistakes. Though currently the issue is usually the model using a figure from and older report. Cross-check redu…
I kinda get it, without experience and trying, how are they to know ( unless they are already 'into it')? After all, corporate training is laughable at best.
Re: KPMG pulls report on AI usage due to apparent hallucinations
#10The crazy thing is the level of effort to say, "have a sub agent validate all references and figures" is so low. I'm paraphrasing, but you don't need much more than that. It would have prevented 99% of the face palms. I use this regularly for my personal financial research system. Even flagship models make mistakes. Though currently the issue is usually the model using a figure from and older report. Cross-check redu…