Topic · 2 articles

Memory

November 20261

  • Compaction: Keeping Long-Running Agents Coherent

    Compaction is lossy compression and you are choosing the loss function. Anthropic's own probe of a compacted transcript recovered 3 of 3 high-level facts and 0 of 3 specific numbers — which is exactly what summarization is supposed to do, and exactly how an agent forgets the constraint it was given forty turns ago.

    Series · Part 199 min readAI EngineeringAI AgentsContext Engineering

August 20261