[Nerd_Nest]

I’m still torn on this. On one hand, memory could make ChatGPT more useful, especially for people using it regularly for work or coding. But on the other hand, the idea that it “remembers” me just feels a little uncomfortable.

I’d want more control over what’s remembered and when. Curious if anyone here has used this yet — is it actually helpful in practice?

[diggan]

> I’d want more control over what’s remembered and when. Curious if anyone here has used this yet

I use the "memory" feature of ChatGPT, and taking a look right now, it seems to have about ~30 items saved from me, some of them are like "Is using egui for a UI task, particularly related to configuring smooth automatic scrolling in a scrollarea." which is useful for maybe the ~3 chats I had about it, and also other things like "Prefers more accuracy in terminology and is looking to represent LLMs in a detailed and structured way." that are more broadly applicable.

Then you can obviously remove any of them, and also manually add by telling it explicitly you want something added.

I'm not sure of its usefulness, I guess it's nice that it correctly "knows" I'm mostly on Arch Linux most of the time but have my servers with NixOS, so if I ask it to create new unix commands I usually get something that works on both, or two versions. But sometimes it also incorrectly infers something because I didn't specify otherwise in the prompt and didn't think of it, but it could see something from the memories.

[logic_node]

I’ve been trying it out recently, mostly for writing and summarizing research. The memory feels subtle so far — it doesn’t jump in unless you really build on past prompts.

That said, I totally agree about control. I wish there was a more obvious way to “pause” or “reset” memory mid-session instead of diving into settings. It’s useful, but still a little opaque.