SecondSourceJudgment rebuilt from primary sources
Research · Jul 19, 2026

Where should an agent's "memory" live? Lay the tree out.

Research notes · Tracking update

From the Jul 19, 2026 daily brief

Yesterday's July 18 issue introduced MemCon from a UCLA-affiliated team in these research notes — making an agent's when-to-read, when-to-write memory decisions learned rather than hand-coded rules (arXiv, Jul 15). Placing it in the trend tree this brief maintains makes its position clearer:

Long context (settled 2024)read a huge corpus at once — an entire codebase
The memory war (in progress)remembering you across sessions — does it land in external memory or in model weights?

Open ?

Opposing claimthe weights side: distilling knowledge into parameters (the cartridges / continual-learning line)

The call this brief has already made: the memory war is unsettled, and current evidence leans toward the context side. "Context" here means the working window the model can read right now; explicit memory is, at bottom, the engineering of continually putting what matters back into that window. The most direct mechanistic evidence: today's naive approaches to writing facts straight into model weights are wildly unstable — what gets written in is washed away by subsequent training, while the same facts placed back in context remain almost fully usable. What would prove this wrong (the threshold is this brief's own tracking standard, not an external one): if within 12 months two or more frontier labs put weight-level memory writing into production services, this judgment is void and flips; verdict date July 14, 2027.

Subscribe free — first issue lands tomorrow morning

Just an email address, unsubscribe anytime. This is the only thing we ask of you.

More in this section