This is just making it more expensive for everyone else, right?

How Claude handles its sessions is none of my business. I'm going to let them do the best they can to provide good service for everyone, and if they can't/won't, I'll switch to a provider that can.

Using these massive models is already pretty danged extravagant, I'm not going to demand to be at the front of the queue at all times, too.

▲

s0ck_r4w 2 hours ago | parent | next [-]

How do a few extra requests with the same prefix make it more expensive for everyone else?

▲

SwellJoe 2 hours ago | parent | next [-]

Keeping a conversation with a very large model active requires hundreds of GB of memory. If my conversation can never be swapped out, like when I go to lunch or take an afternoon walk, that's several hundred GB not available for other users. If everybody does that, Anthropic needs even more infrastructure than the quarter trillion dollars in infra they're already using.

▲

s0ck_r4w 2 hours ago | parent [-]

The idea here is that your conversation is being swapped out for no good reason. The session is still active, as the subagents continue to make progress.

How is this comparable to going to lunch or taking a walk?

▲

SwellJoe 2 hours ago | parent [-]

Is that actually happening, though?

	▲	devnonymous an hour ago \| parent [-]
		Yes https://github.com/izeigerman/claude-thermos/blob/main/src%2...

▲

sznio 2 hours ago | parent | prev [-]

you use more memory?

▲

pkulak an hour ago | parent | prev | next [-]

Eh, I assume Anthropic prices queries somewhere in line with their actual costs. If they don't, and they misalign incentives instead, that's kinda on them.

▲

devnonymous an hour ago | parent | prev [-]

From the README:

> Detect the danger window. When the main lineage goes idle and a subagent is actively running, the main prefix is at risk of expiring.

So, this is not demanding to be at the front of the queue, it's just paying someone to take the place you already had in the queue, when you want to take a leak.

▲

SwellJoe an hour ago | parent [-]

A subagent running doesn't mean that much, though. I often walk away while the subagents are chewing.

	▲	devnonymous an hour ago \| parent [-]
		The defaults seem sensible. This isn't keep-alive-forever by default solution.