How to Fix Your AI Memory in 10 Minutes

The exact guide to stop ChatGPT, Claude, and Gemini from getting worse over time.

Why Your AI Is Getting Worse

Every time you use ChatGPT, Claude, or Gemini, it quietly saves details about you into a memory profile. Your job, your preferences, random questions you asked at 2am — it all goes in.

The problem? These systems have no concept of what actually matters. A throwaway question about a pasta recipe gets the same weight as your core work preferences. Over time, your AI builds a hallucinated version of you — and every response gets a little less useful.

This is the same mistake Spotify made. Listen to one random song and your entire Discover Weekly shifts for months. The fix? The same one Spotify users figured out years ago: clean up what the algorithm hoards, and stop feeding it junk.

Here's exactly how to do it on all three platforms.

Step 1: Audit Your Memory (Find the Junk)

Open your AI's memory file. I guarantee half of it is random garbage from months ago.

ChatGPT

1. Open ChatGPT → click your profile icon (bottom-left)

2. Go to Settings → Personalization → Manage Memories

3. You'll see a list of everything ChatGPT "remembers" about you

4. You can also type: "What do you remember about me?" in any chat and it'll list them

Claude

1. Open Claude → click Settings (gear icon)

2. Go to Capabilities → Memory

3. Click individual memory items to view what's stored

4. Or type in any chat: "What do you know about me from memory?"

Gemini

1. Open Gemini → click the Settings gear (bottom-left)

2. Select Personal context

3. Scroll through your saved facts

4. Direct link: gemini.google.com/personal-context

Step 2: Delete Everything That Doesn't Belong

Be ruthless. If a memory isn't actively helping you get better responses, it's actively making them worse. Delete anything that's:

• ❌ Outdated (old projects, former preferences)

• ❌ Random (one-off questions that got saved)

• ❌ Wrong (things it misinterpreted)

• ❌ Irrelevant (it doesn't need to know you asked about sourdough bread once)

How to delete:

ChatGPT: Click the trash icon next to each memory in Manage Memories. Or tell it: "Forget that I mentioned [X]"

Claude: Click on a memory item → delete. Or tell it in chat: "Forget what I said about [X]"

Gemini: Three-dot menu next to each entry → Delete. Or tell it: "Forget that I mentioned [X]"

⚠️ Important: On ChatGPT, deleting a chat does NOT delete the memories it created. You have to delete memories separately.

Step 3: Put What Matters in Custom Instructions

The memories you actually DO want your AI to know? Don't let it save them automatically. Put them in Custom Instructions instead.

Custom Instructions are a separate system — they don't get polluted by random conversations. They stay exactly as you wrote them, every single time.

ChatGPT

1. Settings → Personalization → Custom Instructions

2. Two fields:
   • "What would you like ChatGPT to know about you?" → Your role, expertise, preferences
   • "How would you like ChatGPT to respond?" → Tone, format, length, style

Claude

1. Create a Project → Add Project Instructions

2. Write your context and preferences there

3. Every conversation in that project uses your instructions — no memory pollution

Gemini

1. Settings (gear icon) → Personal context

2. Find "Your instructions for Gemini" → Click Add

3. Write standing instructions that apply across all chats

4. Direct link: gemini.google.com/personal-context

What to put in Custom Instructions:

Here's a template — fill in the blanks:

I'm a [your role] working on [what you do].

When I ask questions, I prefer:
- [format preference: bullet points / paragraphs / code-first]
- [length: concise / detailed / depends on topic]
- [tone: casual / professional / technical]

Things to always keep in mind:
- [core preference 1]
- [core preference 2]
- [tool/language/framework you always use]

Don't:
- [thing that annoys you]
- [unnecessary behavior to avoid]

Step 4: Use Temporary Chat for One-Off Questions

This is the one nobody talks about.

Every random question you ask — a recipe, a quick fact check, a one-off coding problem — feeds into your memory profile and dilutes it. The fix: Temporary Chat.

Think of it like incognito mode for your AI. It doesn't read your memories, and it doesn't create new ones.

ChatGPT

• Click the model dropdown at the top → select "Temporary Chat"

• Or look for the temporary chat toggle when starting a new conversation

Claude

• Click the ghost icon 👻 in the upper-right corner when starting a new chat

• This opens an incognito conversation — not saved, not used for memory

Gemini

• Start a Temporary Chat from the new chat menu

• Won't reference your memory or save to your Activity

When to use Temporary Chat:

• 🍳 Cooking recipes

• 🔍 Quick searches or fact-checks

• 💻 One-off coding problems

• ✈️ Travel research for a trip you'll take once

• 🎲 Anything you wouldn't want influencing your AI permanently

Step 5: Repeat Monthly

None of these companies have built memory decay yet. Until they do (and it could take years), your AI will keep hoarding every random thing you've ever said.

Monthly cleanup checklist:

• Open memory settings on each platform you use

• Delete outdated or irrelevant memories

• Check for contradictory entries (it happens more than you think)

• Update your Custom Instructions if your work or preferences changed

• Set a reminder for next month

Pro tip: Set a recurring calendar reminder — first of every month, 10 minutes. That's all it takes.

Why This Works

AI memory pollution is a system-level problem — you can't fix it with a better prompt. But you can work around it:

The difference is night and day. I do this regularly and the quality improvement is immediate every single time.

Quick Reference