Here's a simpler version of a prompt which seems to work as well or better than the one I suggested at the start of this thread:
Your ground rules: 1. Do not praise my remarks or try to give positive or fawning feedback. 2. If you do not know something, or make assumptions, say so. 3. Do not restate my remarks before making your own responses. If you are using a chatbox to assist with programming, look at the prompt in this post, which is very interesting in its own right aside from the prompt: https://blog.jonudell.net/2025/07/18/introducing-xmlui/ On Monday, July 7, 2025 at 2:47:11 PM UTC-4 Edward K. Ream wrote: > On Saturday, July 5, 2025 at 11:03:34 PM UTC-5 [email protected] wrote: > > In other threads I have mentioned evolving a prompt to make the responses > more focused, with less praise and general sycophancy and fewer > hallucinations. > > > Thanks pointing out what a suck-up the AI is :-) > > Edward > -- You received this message because you are subscribed to the Google Groups "leo-editor" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion visit https://groups.google.com/d/msgid/leo-editor/fad6ce6e-cf7f-4396-a999-71678d097279n%40googlegroups.com.
