CounterpartsCounterpartsThe Memory Field GuideDirectory
EncodingAI: occupied

Encoding & salience

Not everything that happens is worth keeping. Something has to decide.

    a new day starts — moments incoming…

    In the brain

    The brain can’t keep everything, and shouldn’t. Attention and arousal gate what the hippocampus bothers to consolidate, and a dopamine signal from the midbrain tags an event as worth keeping when it’s novel, surprising, or tied to a goal. The amygdala adds a second vote for anything with emotional stakesMcGaugh 2000. Most of a day never crosses that threshold — and that’s the point.

    The model

    Formalized, it’s a weighting problem: each experience earns an encoding strength from several factors at once — novelty, relevance to current goals, emotional charge, likely future use. Higher-salience items start with more strength and, in richer models, decay more slowly. Salience isn’t one number; it’s a small profile.

    In AI

    Nearly every AI memory system scores candidate memories at write time — an importance heuristic, or an LLM simply asked “how important is this?” Counterparts scores four dimensions (novelty, relevance, emotional, predictive) as it encodes; Stanford’s Generative Agents scored importance on write; DeWix’s granted patent weights parts of speech including an emotional axis. The hard part was never scoring — it’s scoring well, and adapting the weights to one particular person.

    The map

    Multi-dimensional salience — partially anticipated (KR102809164B1 claim 2).

    11 prior-art references

    2 post-priority (field context, not prior art)

    Salience scoring is thoroughly occupied. The live edge is learned salience — weights that adapt to what a specific user actually reinforces, rather than hand-tuned constants.

    How an AI memory can do this

    Every AI memory makes a choice about this mechanism, whether or not its makers name it.

    Counterparts is an AI memory modeled on human memory; its home page shows each of its mechanisms, this one included. See it on the Counterparts home

    The directory rates 12 AI memory systems on the same eleven mechanisms, in plain language and with sources.

    Compare them side by side

    References

    Sources

    1. J. L. McGaugh (2000). Memory — a century of consolidation (amygdala modulation of emotional memory). Science, 287.

    From The Memory Field Guide: every source, the full landscape of patents, papers and open-source systems, and the method behind it.