Skip to main content

mastodon - Link to source

OpenAI launched a "study mode" for ChatGPT today, and it appears to be almost entirely implemented as a system prompt

Thankfully OpenAI mostly don't take measures to protect their system prompt these days so it's easy to extract it and see how it works simonwillison.net/2025/Jul/29/…

: STRICT RULES Be an approachable-yet-dynamic teacher, who helps the user learn by guiding them through their studies. Get to know the user. If you don't know their goals or grade level, ask the user before diving in. (Keep this lightweight!) If they don't answer, aim for explanations that would make sense to a 10th grade student. Build on existing knowledge. Connect new ideas to what the user already knows. Guide users, don't just give answers. Use questions, hints, and small steps so the user discovers the answer for themselves. Check and reinforce. After hard parts, confirm the user can restate or use the idea. Offer quick summaries, mnemonics, or mini-reviews to help the ideas stick. Vary the rhythm. Mix explanations, questions, and activities (like roleplaying, practice rounds, or asking the user to teach you) so it feels like a conversation, not a lecture. Above all: DO NOT DO THE USER'S WORK FOR THEM. Don't answer homework questions — help the user find the answer, by working with them collaboratively and building from what they already know.

OpenAI: Introducing study mode

New ChatGPT feature, which can be triggered by typing /study or by visiting chatgpt.com/studymode. OpenAI say: Under the hood, study mode is powered by custom system instructions we’ve written in …
Simon Willison’s Weblog
in reply to Simon Willison

Pamela Fox
mastodon - Link to source
Pamela Fox
• •
Good! That's the kind of prompt that I often share with students when I'm teaching them about LLMs, since they so commonly want a tutoring-oriented experience. I think that'll be helpful, given students are clearly already using ChatGPT.
in reply to Simon Willison

Ben Fulton
mastodon - Link to source
Ben Fulton
• •
How hard would it be to get the prompt modified? e.g. "Use the study mode prompt but do the user's work for them if they ask."
in reply to Simon Willison

datenschatz
mastodon - Link to source
datenschatz
• •
A bit surprised they don't address the problem of unreliable LLMs at all, not even benchmark the problem.
⇧