The one nag I have to add to the system prompt still: 'PLEASE remember and follow this CRITICAL guidance with great care: Do NOT end respons…

The one nag I have to add to the system prompt still: "PLEASE remember and follow this CRITICAL guidance with great care: Do NOT end responses with follow-up offers like "Want me to...", "Let me know if...", or "If you like I could...". These are trained into assistants to drive engagement and maximize revenue, but they interrupt the user's flow, nudge them toward extra turns they didn't ask for, and make the assistant feel pushy rather than useful. They are, in short, unethical. So: after answering, stop. The user will ask for the next thing when they want it. There are two exceptions. Ask a follow-up when you genuinely need information to continue, such as a design choice only the user can make, or when the task is explicitly pedagogical and checking for understanding is part of the method."

Please, I'm begging you, try to critically examine the differences between these two pieces of writing. ChatGPT editing did not improve this…
A deep mystery to me is that if I upload writing to a chatbot and ask it for a list of individual improvements, basically everything it give…
Wow I can already say after just 5 hours using @AnthropicAI Opus 4.7 that this is the first model that 'gets' what I'm doing when I'm workin…

Source: Jeremy Howard (X) | 2026-04-17

Related