Context Compaction

topic on 2 shows · 3 statements across 3 episodes

Latent Space the MAD Podcast

3 statements about Context Compaction, every show

LATENT SPACE Assertion Not checkable as stated
Biderman: Harmless enterprise queries on frontier models cost thousands of dollars
“And now you can solve these tasks with frontier models and compaction. And when you ask them to do so, they will consume thousands of dollars for queries that we think are harmless. That every employee in the company would be able to answer.”
Dan Biderman Jul 13, 2026 ▶ 25:50 The AI Memory Problem: Why Long Context Isn’t Enough — Dan Biderman, Engram Co-founder & CEO
MAD Insight
Chase: AI agent context compaction must retain recent messages for flow
“You want to keep around like the last N messages, let's say the last like 10 or so messages, because if you compact everything, it actually like throws it off completely.”
Harrison Chase Mar 12, 2026 ▶ 21:03 Everything Gets Rebuilt: The New AI Agent Stack | Harrison Chase, LangChain
Nelle: Sub-agents provide an architectural boundary to compress agent context cleanly
“And then the other reason to use sub-agents is we want, ah, contexts to be sort of summarized, reduced down at a sub-agent level. That's a really neat boundary at which to compress that rollout and testing into a final message that that agent writes that then…”
Jonas Nelle Mar 6, 2026 ▶ 47:18 Cursor's Third Era: Cloud Agents — ft. Sam Whitmore, Jonas Nelle, Cursor

← every entity, every show

Made with StarZero

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.