All sessions
Memory & Continual LearningSession
Lessons from Studying Every Memory System
Shlok Khemani
- When
- Wednesday, July 13:20 PM – 3:40 PM · 20 min
- Where
- Track 3San Francisco, CA · imported from ai.engineer's public schedule feed
About this session
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
More in Memory & Continual Learning
- Beyond Static Intelligence: Evaluating Continual LearningWednesday, July 1 · 10:45 AM – 11:05 AM · Track 3
- Scaling up Continual LearningWednesday, July 1 · 11:10 AM – 11:30 AM · Track 3
- Memory Harnesses for Long-Running Research AgentsWednesday, July 1 · 11:40 AM – 12:00 PM · Main Stage
- Scaling Compute on ContextWednesday, July 1 · 11:40 AM – 12:00 PM · Track 3
- Intelligence + Continual Learning = ExpertiseWednesday, July 1 · 12:05 PM – 12:25 PM · Track 3
For developers: this programme is open data — JSON, iCal, schedule XML and an MCP endpoint.Show endpointsHide
- JSONEvery published session and speaker, in one request./aie-worldsfair-2026-import/feed.json
- iCalSubscribe in Google, Apple or Outlook Calendar./aie-worldsfair-2026-import/feed.ics
- Schedule XMLfrab / pentabarf — the format conference apps import./aie-worldsfair-2026-import/feed.xml
- MCP + RESTPoint Claude at the programme. OpenAPI 3.1 included./agents
No key, no signup, CORS open. Everything here is generated from the same data the organisers edit.