News for hackers. Stuff that matters.
Re:Show HN: Claude-thermos – keeps your Claude session warm ... by supern0va on Thursday July 23, 2026 @03:53PM (#49027144)
Can you expand on this? I can't imagine this is holding up an entire machine or materially impacting capacity. Isn't it common to have a tiered cache and to ultimately evict (or move to another tier) if there's an active inference request and no available capacity elsewhere?
Re:Show HN: Claude-thermos – keeps your Claude session warm ... by Lalabadie on Thursday July 23, 2026 @04:00PM (#49027241)
Yes, however if a tool like this commoditizes a way to stay "higher" in the cache hierarchy to avoid getting dropped, then for the same total capacity, Anthropic have to become stricter about retention.
Re:Show HN: Claude-thermos – keeps your Claude session warm ... by supern0va on Thursday July 23, 2026 @04:32PM (#49027639)
It's unfortunate that there isn't some better way to signal that there's a high chance that a turn is coming (ie, due to active sub-agents). If CC could send a ping saying "I don't need a turn, but please keep this cached at some tier because there will be a turn soon." that would probably help with cache efficiency. Instead, it seems like there's just the shotgun one-hour solution.