Memory: how AI agents remember

About this episode

How AI agents and chat apps remember you when the model itself can't: where memory really lives, what's worth saving, the three ways a note comes back, notes for long jobs, and what goes wrong, from stale notes to memory poisoning, plus the background tidy-up the labs now call dreaming.

Written by Kiran Krishna. Narrated with an AI voice. · LinkedIn

In this episode

1. 0:01When OpenAI added memory to ChatGPT in 2024, it gave an example.
2. 1:06Here's the plan.
3. 1:18So where does memory live, if not in the model?
4. 3:12So what's worth saving?
5. 4:38So how does a note get back into the form?
6. 7:11So what about one job that's too big for one form?
7. 8:35So what goes wrong?
8. 10:42So who told it about the jellyfish?