News for hackers. Stuff that matters.
Re:Δ-Mem: Efficient Online Memory for Large Language Models by in-silico on Saturday May 16, 2026 @06:47PM (#48164439)
I think you underestimate just how much information 100M words-ish of information is. It's like a 300,000 page novel. That's a 50 foot (~15 meter) thick book.

Surely with (much less than) 300K pages you could describe every meaningful detail of a video series' plot. You don't need to remember the exact pixel values.

You can also scale the numbers up. I specifically chose a relatively small model and short context length as a reference, so 100x bigger is not out of question. At that point, with a 10B token capacity, you are looking at all of English Wikipedia in a single state.

There are no comments on this comment yet.