breaking up with ChatGPT? Here’s How To Transfer Everything It Knows About You To Claude
If you are one of the 1.5 million people who cancelled their ChatGPT subscription this week (as stated by Forbes), you will appreciate this guide on how to transfer everything it knows about you over to Claude.
Picture this: you’ve spent the better part of a year training ChatGPT. Not with flashcards. Not intentionally. Just… living your online life. You told it you’re a vegetarian. That you run a business. That you prefer bullet points over walls of text and that it should never, ever start a sentence with “Certainly!”
As an affiliate partner of various brands and sponsored content, HerPaperRoute may earn commission on qualifying purchases. Disclaimer
And now you’re curious about Claude, but the thought of re-explaining yourself from scratch sounds exhausting.
Here’s the good news: you don’t have to. Anthropic built a tool specifically to yoink everything ChatGPT knows about you and drop it straight into Claude’s memory. The whole thing takes about two minutes, tops. Here’s how.
Breaking Up With ChatGPT? At Least Take Your Stuff
First, A Quick Explainer on What “Memory” Actually Is. Think of AI memory less like a diary and more like a sticky note on the fridge. It’s not your full chat history.
It’s the shorthand: your name, your job, the fact that you work from home, that you hate being talked down to, that you’re building a business and need Claude to act like a strategist, not a search engine.
ChatGPT has been quietly collecting these sticky notes every time you interacted with it. Custom instructions count too, those two fields you may or may not have filled out telling it who you are and how you like to be spoken to.
The goal here isn’t to import every conversation. It’s to import the you that the other AI already knows, so Claude can skip the awkward first-conversation energy.
Step 1: Make ChatGPT Tell You Everything It Knows
Open a new chat in ChatGPT. Copy this prompt (written by Limited Edition Jonathan) and paste it into ChatGPT in verbatim:
I'd like you to create a comprehensive personal context file about me based on everything you know. I want to keep a portable copy of the context we've built together - my preferences, workflows, projects, and anything else you've learned about how I work. Pull from your memory system, our conversation history, my custom instructions, and any patterns you've picked up.
Structure the output using the sections below. Skip any that don't apply to me.
<identity>
Name, job title or role, company or organization
What I actually do day-to-day (not just my title)
Industry and domain
</identity>
<technical-environment>
Operating system and hardware
Software, tools, and platforms I use regularly
Programming languages or technical skills (if applicable)
Specific versions, configurations, or setups you know about
</technical-environment>
<active-projects>
What I'm currently working on
Short-term goals and long-term objectives you're aware of
Recurring tasks or workflows
</active-projects>
<expertise>
Topics I know deeply
Topics I'm actively learning
Areas where I'm a beginner or have asked for extra explanation
</expertise>
<communication-preferences>
How I like responses structured (length, format, tone)
Things I've asked you to do or not do
Formatting preferences (bullets vs prose, technical depth, etc.)
Pet peeves or repeated corrections
</communication-preferences>
<writing-style>
How I write (formal, casual, technical, etc.)
Voice characteristics you've observed
Specific style rules I've mentioned
</writing-style>
<key-people>
Collaborators, team members, or clients I mention frequently
Reporting structure or key professional relationships
People I've asked you to help me communicate with
</key-people>
<personal-context>
Location and timezone
Personal interests or details relevant to our work
Constraints or preferences (accessibility needs, scheduling, etc.)
</personal-context>
<standing-instructions>
Anything from my custom instructions or system prompt
Rules I've set that you always follow
Recurring corrections that have become permanent instructions
</standing-instructions>
<workflow-patterns>
How I typically use you (brainstorming, editing, coding, research, etc.)
Common request types and how I like them handled
Multi-step processes we've developed together
</workflow-patterns>
Be thorough. I want a complete snapshot, not a summary. If you know it, include it. Keep the section tags in the output so it stays organized and portable.ChatGPT will spit out a tidy code block with everything it knows about you.
Step 2: Copy the Output and Head to Claude’s Import Tool
Go to claude.com/import-memory if you are new to Claude. Or if you already have an account, go to claude.ai/settings/capabilities.
You’ll see a simple text box and a big friendly button that says “Add to memory.” Paste your exported text in there and click it.
Claude will parse the information and start storing it as individual memory entries. The whole import processes in the background, and you’ll see your updated memory within about 24 hours. Once it’s done, you can test it by starting a new chat and asking: “I updated my memory. What did you learn about me?”
That’s the whole thing. two steps, two minutes.
A Few Things Worth Knowing
Memory on Claude is available on all plans, including the free tier. You don’t need a paid subscription to use the import tool or to have memory active going forward.
Claude stores your memories separately from your chats. Nothing bleeds between conversations. If you use Claude for both work and personal stuff, it keeps that context partitioned so your client strategy sessions don’t contaminate your recipe searches.
You can see and edit everything Claude remembers. Go to Settings, then Capabilities, then “View and edit your memory.” You can read every entry, delete anything you don’t want there, and add new things manually. It’s genuinely transparent in a way that feels rare.
Claude’s memory is encrypted and not used to train the model. That’s a meaningful distinction from some competitors, where importing your data means it also trains their AI going forward.
Read this next:
Follow along on Instagram!
