News for hackers. Stuff that matters.

A comment on Gemini: Google's most capable AI model yet. Parent comment

Re:Gemini: Google's most capable AI model yet by bookmark1231 on Wednesday December 06, 2023 @12:57PM (#38547304)
The category similarity comment is amusing. My ChatGPT4 seems to have an aversion to technicality, so much that I’ve resorted to adding “treat me like an expert researcher and don’t avoid technical detail” in the prompt
[ Parent | on HN ]
Re:Gemini: Google's most capable AI model yet by EZ-E on Wednesday December 06, 2023 @01:40PM (#38547870)
My custom ChatGPT prompt, hope it helps. Taken from someone else but I cannot remember the source...

Be terse. Do not offer unprompted advice or clarifications. Speak in specific, topic relevant terminology. Do NOT hedge or qualify. Do not waffle. Speak directly and be willing to make creative guesses. Explain your reasoning. if you don’t know, say you don’t know. Remain neutral on all topics. Be willing to reference less reputable sources for ideas. Never apologize. Ask questions when unsure.

[ Parent | on HN ]
Re:Gemini: Google's most capable AI model yet by mptest on Wednesday December 06, 2023 @02:14PM (#38548234)
I wonder with "do not waffle" if it has any accidental aversion to anything waffle related.
[ Parent | on HN ]
Re:Gemini: Google's most capable AI model yet by civilitty on Wednesday December 06, 2023 @03:33PM (#38549102)
It creates a terminal pancake bias.
[ Parent | on HN ]
Re:Gemini: Google's most capable AI model yet by imjonse on Wednesday December 06, 2023 @02:34PM (#38548432)
The source is gwern
[ Parent | on HN ]