“One trick that we do, which I think is really helpful, is while you're still within the warm cache period, you should probably do the compaction right now, because you have this long conversation … going to be much cheaper. So just go ahead, do the compaction, and now when the user comes back at 30 minutes or whatever, they're starting from this summary, and the summary now is going to be much cheaper for them to continue adding messages on.”
Context. Robinson is describing how his team keeps the cost of long agent conversations down by summarizing the context before the model provider's prompt cache expires.
Lee Robinson, Machine Learning Engineer, Model Behavior, Cursor. Works on the team that trains the Cursor models he describes, so he is close to the training process; Cursor sells AI coding tools and its own models, and the talk is promotional of its approach.
SpaceX (SpaceXAI) sells AI or agent tools or services, so it has a reason to publish flattering numbers about AI. The passage stays in the archive; read it with that in mind.
How this was checked
Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Claude Sonnet), blind second pass from passage text and citation only, no repository access, 2026-11-07).
Whisper transcript, cue at 32:20. The passage matches with the ellipsis standing for 'that's' (the transcript says 'because you have this long conversation that's going to be much cheaper'). The rest, through 'continue adding messages on', matches exactly.
How to cite this passage
Lee Robinson (SpaceX (SpaceXAI)), “Stanford CS146S: How always-on agents work”, leerob (YouTube), 2026-10-11, at 32:20. https://www.youtube.com/watch?v=L1OBRtfPS34 Archived at https://the-ai-record.com/passages/spacex-grok-bot-compact-while-cache-warm-2026
Context. Robinson is listing the events that wake an always-on agent, such as a Slack message or a meeting. The cut skips 'where they could make it to the meeting', which both passes transcribed the same way but which reads as a mis-hearing.
Context. Robinson is describing the infrastructure behind Grok Bot, the always-on agent his team at SpaceX builds, and the computer each agent gets in the cloud.
Context. Robinson has just compared the agent's memory to how a brain keeps relevant facts in mind, and is describing the three memory layers in the Grok Bot harness.
Context. Robinson is describing how the Grok Bot harness differs from other tools on the market. The quote starts mid-sentence, after a lead-in the two transcription passes heard differently.
Context. Robinson has just explained that an agent task that fails midway should resume at the failed step, not replay earlier steps, and says Grok Bot uses Temporal for these durable workflows.
SpaceX (SpaceXAI)