Markdown source

Lessons from Studying Every Memory System

Conference Context

Session Description

For the past year I've done one thing obsessively: studied how AI products implement personalization. I've reverse-engineered the memory systems inside ChatGPT, Claude, Gemini, and Poke, and helped consumer teams build their own. In this talk, I'll trace the evolution of ChatGPT and Claude memory over the past three years. I'll then share lessons learnt from studying these systems and share thoughts on where I think memory for consumer is heading.

Media Evidence

No related AI Engineer channel video found yet.

Evidence Graph

This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

Media Signals

No linked video, transcript, or slide source has been attached yet.

Agent Reading Notes

Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

Transcript Status

No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

People

Notes

Synthesis

Synthesized Breakdown

Lessons from Studying Every Memory System ## Conference Context - Date/time: 2026-06-30 · 3:20pm-3:40pm - Track/room: Memory & Continual Learning · Track 3 - Speaker(s): Shlok Khemani - Session type/status: session · confirmed - Track: Memory & Continual Learning - Room: Track 3 - Session type: session - Status: confirmed ## Session Description For the past year I've done one thing obsessively: studied how AI products implement personalization. I've reverse-engineered the memory systems inside ChatGPT, Claude, Gemini, and Poke, and helped consumer teams build their own. In this talk, I'll trace the evolution of ChatGPT and Claude memory over the past three years. I'll then share lessons learnt from studying these systems and share thoughts on where I think memory for consumer is heading.

Speaker And Company Context

Topics Covered

Derived Links And Source Material

Novel Concepts / Clever Methods

Evidence Boundary

This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.