Mnemon: Raw Records, Fast Judgments, Slow Thoughts
Quick summary
arXiv:2609.36059v1 Announce Type: cross Abstract: Long-term memory lets an LLM assistant use a history it can no longer reread, and most memory systems build it by rewriting conversations into facts, graphs or typed memories at write time. We argue that the work of memory divides, as thinking does, into two systems. Most of it is fast System 1 work: many small, independent yes/no judgments about records, such as whether a record is needed or no longer current, which a decision model makes by the dozen in a third of a second. Only a little is slow System 2 work: writing a few search queries, na
Key takeaways
- arXiv:2609.36059v1 Announce Type: cross Abstract: Long-term memory lets an LLM assistant use a history it can no longer reread, and most memory systems build it by rewriting conversations into facts, graphs or typed memories at write time.
- We argue that the work of memory divides, as thinking does, into two systems.
- Most of it is fast System 1 work: many small, independent yes/no judgments about records, such as whether a record is needed or no longer current, which a decision model makes by the dozen in a third of a second.
Why it matters
“Mnemon: Raw Records, Fast Judgments, Slow Thoughts” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments