I have no idea. the single thing I can think of is that it can have a memory.. but you can do that with even less code. Just get a VPS. create a folder and run CC in it, tell it to save things into MD files. You can access it via your phone using termux.

You could, but Claude Code's memory system works well for specialized tasks like coding - not so much for a general-purpose assistant. It stores everything in flat markdown files, which means you're pulling in the full file regardless of relevance. That costs tokens and dilutes the context the model actually needs.

An embedding-based memory system (letta, mem0, or a self-built PostgreSQL + pgvector setup) lets you retrieve selectively and only grab what's relevant to the current query. Much better fit for anything beyond a narrow use case. Your assistant doesn't need to know your location and address when you're asking it to look up whether sharks are indeed older than trees, but it probably should know where you live when you ask it about the weather, or good Thai restaurants near you.

When I use AI to write code, after a week or 2, if I go back to the written code I have a hard time catching up. When I write code by myself I always just look at it and I understand what I did.

a program is function of the programmer, how you code is how you think. that is why it is really difficult, even after 60 years, for multiple people to work on the same codebase, over the years we have made all kinds of rules and processess so that code written by one person can be understood and changed by another.

you can also read human code and empathise what were they thinking while writing it

AI code is not for humans, it is just a stream of tokens that do something, you need to build skills to empirically verify that it does what you think it does, but it is pointless to "reason" about it.

Not only do I have a hard time catching up, but it's like I'm looking at a codebase I've never seen before, even though I absolutely reviewed the code before committing

++Hard Agree.

Could you detail this a bit please

well well well, how the turntables.

You cannot logic someone out of something they didn't logic themselves into. 90% of what we feel is primal in-group survival.

Wow that sounds awesome. I was thinking of doing something like that but never had the time to commit.

the same can be said about any social media. you can block/unfollow/mute anything, but it creeps through anyway.

My problem with all this is that the quality of all the generated text and graphical content is utter garbage. Quantity != quality.

The graphics I've produced are absolutely phenomenal IMHO. I find that that textual content depends highly on the prompt, and often does take quite a few iterations to get right.

Often with text, the GPT is more of an assistant/advisor/proofreader for me, rather than a stand-alone creator of quality content.

Sometimes it works really well for emails. Like for producing responses to formal communications. It can save cut the time to respond from 10 minutes to 30 seconds.

I don't have a good system put in place yet. I tend to write& rewrite interesting things I find and I keep them in separate notes in the hope that one day I'll re-use them somewhere. But it's a mess.

That seems nice! Thank you for the idea.