Re:Google Gemini tried to kill me
by fbnbr on Wednesday June 19, 2024 @09:20PM
(#40733977)
That's an interesting prompt I tried on our Pulze.ai platform Spaces and we nailed it with automatically choosing the right model for this type of question gpt-4-turbo: "Yes, you can infuse garlic into olive oil without heating it up, but it requires caution due to the risk of botulism, a potentially fatal illness caused by Clostridium botulinum bacteria. These bacteria can thrive in low-oxygen environments and can produce toxins in food products like garlic-infused oil if not prepared or stored correctly."
I think that is one advantage of not just blindly trusting one model but finding consensus among many top rated models within one interface that allows you to quickly cross-check.
Re:Google Gemini tried to kill me
by fbnbr on Thursday June 20, 2024 @01:09AM
(#40735118)
Which Gemini was used is important too btw. - just tried Gemini-1.5-pro and it was working just fine. So I really think the newer versions of LLMs are able to catch this.
I think that is one advantage of not just blindly trusting one model but finding consensus among many top rated models within one interface that allows you to quickly cross-check.