Have you tried creating a separate project for language learning and adding your preferences to project instructions?

I'm using the web interface and have it in it's own conversation. I assume the app would be the same thing but maybe it will be better.

Fixed the link! thanks for pointing it out :)

I think ChatGPT is trying to be everything at ones - casual conversation, technical tasks - all of it. And it's been working for them so far!

Isn't representing past conversations (or summaries) as embeddings already storing memories in encoded forms?

I think a few of the things you’ve mentioned in the ChatGPT article are hallucinations. There’s no user interaction metadata about topics, average message length etc., you asked the AI and it gave you a plausible sounding answer. Also the memories / snippets of past conversations aren’t based on like last 30 conversations or so and they aren’t provided to every message. They are doing some kind of RAG prompt injection and they remove the injected context in the next message to not flood the context window. The AI itself seems to have no control over what’s injected and when, it’s a separate subsystem doing that injection.

Summaries are still language based. Embeddings aren't, but the models can't use them as input.

I should've been clearer, but what I meant was language models 101. Normal people don't understand even basics like LLMs are stateless by default and need to be given external information to "remember" things about you. Or, what is a system prompt.

Thanks for sharing this! Seems like I chose exactly the wrong day to write this

It's still very relevant, especially considering their new approach is closer to ChatGPT. But I find it very interesting they're not launching it to regular consumers yet, only teams/enterprise, it seems for safety reasons. It would be great if they could thread the needle here and some up with something in between the two approaches.

Going to dive deeper!

Thanks Simon! I’m a huge fan of your writing

Just blogged about your posts here https://simonwillison.net/2025/Sep/12/claude-memory/

Wow! Thank you for the support Simon :)

Thanks for reading! It was an great experience, yes :)

This is beautiful and great for gifting. Thank you.

Sal Khan (founder of Khan Academy) had a decent analogy for what AI is doing to creative fields in the No Priors Podcast: https://www.youtube.com/watch?v=NH95LKOILgE&t=2626s&ab_chann...:

The camera is the best metaphor. In the 19th century, being an artist was a real thing; it was really a technical field. You were a portrait painter and the best artists would study for years to be as accurate to reality as you could - look at how the light moves and all of that. All of a sudden, the camera comes out and artists fear this is the end of art because this new thing can capture reality better than anyone can.

But then very quickly, people realized that in some ways this liberates the artists. It's not a coincidence that the impressionist movement coincided with the advent of the camera. People realized it's not about capturing reality but the expression and feelings conjured. This led to an explosion about what art is and come out of the trap about painting, nobility, and grand scenes into things that really evoke and challenge us.

People are now saying AI can write pretty well. It can code pretty well. It can create movies, images pretty well. What that tells me is that it liberates the creator to move beyond that. Someone can elevate and integrate and manage these tools.