I always though it was something you said to kids. Not actually something you forced them to do. Like telling kids their eyes will turn to squares if they watch too much TV.

I’m sorry to hear that it happened to you.

If you have enough regular ram and an nvme ssd you can run huge models on modest hardware using Colibrí.

I got a Lenovo mini PC with 64GB of ram and a 500GB nvme and a 38B model runs with 11 tokens per second on my machine.

The 38B model fits in my ram but if I had used a 120B parameter model then it would stream the rest of the model from my nvme disk.

Sure, but I still think calling it “memories” is a reach and a bit disingenuous. It’s not remembering anything. It’s re-reading it will the every run, making it appears as if it has remembered. Calling it “reminders” or something else I think would me more appropriate.

The “memories” terminology comes from the big AI companies and they are doing everything in their power to make AI seem smarter than it actually is. A lot of reporters in media has a hard time understanding this as well and will report on AI as having it’s “own thoughts” and “making own decisions”.

ChatGPT breaches confinement because their engineers are stupid. Not because of some self determination to fuck with us or our infrastructure. OpenAI are responsible and let it happen. Same with Anthropic.

In the end an AI is a dumb computer program that only know and does what we tell it to do.

Yes I would say that she temporarily learns something while reading the notes. And she stores it in short-term memory.

The difference with AI though is that it has to re-read the same note again and again after each question you ask it. It does not keep things in “memory” from your previous conversations. It reads it again before answering you.

That is why context length matters and is important in LLMs. There’s a huge difference between talking to an AI with 10k in context length and 1mil in context length. You can try it yourself using Llama.cpp and running LLMs locally.

The AI is no different from the girl in “50 First Dates (2004)”. It has to go back and read the post-it notes every time you start a new session. It does not retain memory without writing shit down to read later.

Does an Alzheimer’s patient learn things just because they read the same note every morning explaining the reality to them?

They save some strings in a document to later read and “remember”. Calling them memories is a reach.

In Sweden you are allowed to make copies for private useage. I can record and save whatever piece of media I want, as long as I don’t distribute it to other people and the material itself is not illegal (abuse material for example).