16 points | by hypervs 3 days ago ago
2 comments
Kind of reminds me of how redis forks itself to have a snapshot to persist as a backup.
Checkpointing the live continuation shifts recovery cost toward retained state rather than lifetime event count, which seems especially useful for agents with many completed tool calls.
Kind of reminds me of how redis forks itself to have a snapshot to persist as a backup.
Checkpointing the live continuation shifts recovery cost toward retained state rather than lifetime event count, which seems especially useful for agents with many completed tool calls.