The Memory Problem, Baseten | Compile 26
Source title: The Memory Problem, Baseten | Compile 26. Source description: Mudith Jayasekara, Charlie O'Neill, and Harry Partridge of Baseten's research team on the memory problem for long-horizon agents: compressing the KV cache to get near-lossless retrieval of relevant context at inference time. 00:00 The memory problem 03:15 Selection vs. synthesis 04:22 Amortization and sparse autoencoders 05:38 Compressing the KV cache 08:39 Iterative compaction 10:41 A compacted cache is an MLP
youtube.comReach people exploring AI agents
See placements →What happened
Source title: The Memory Problem, Baseten | Compile 26. Source description: Mudith Jayasekara, Charlie O'Neill, and Harry Partridge of Baseten's research team on the memory problem for long-horizon agents: compressing the KV cache to get near-lossless retrieval of relevant context at inference time. 00:00 The memory problem 03:15 Selection vs. synthesis 04:22 Amortization and sparse autoencoders 05:38 Compressing the KV cache 08:39 Iterative compaction 10:41 A compacted cache is an MLP
Reported by CursorMore details
About this account
The title and description alone do not establish the agent autonomy level.
Agents In Use pipeline: video selected by TypeSafe Jev using source title/description only; recording and outcomes not independently verified.
Credit: Cursor
Source published 29 Jun 2026
Source checked 14 Oct 2026
Tools and topics
AI agent
video · agent-demo
Editorial completeness: 75/100. Measures documented fields, not agent performance or verified outcomes.
Video notes
Cursor · YouTube
- Source title: The Memory Problem, Baseten | Compile 26