Unverifiable software stack now amplified with LLM undetermistic. This while thing starts to feel like we are building on top a giant house of card!
Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
371–380 of 695 posts
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#372Claude has gotten noticeably worse for me too. It goes into long exploration loops for 5+ minutes even when I point it to the exact files to inspect. Then 30 minutes later I hit session limits. Three sessions like that in a day, and suddenly 25% of the weekly limit is gone. I ended up buying the $100 Codex plan. So far it has been much more generous with usage and more accurate than Claude for the kind of work I do.…
When they bumped the context size up to 1m tokens they made it much easier to blow through session limits quickly unless you manually compact or keep sessions short.
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#373Hey all, Boris from the Claude Code team here. We've been investigating these reports, and a few of the top issues we've found are: 1. Prompt cache misses when using 1M token context window are expensive. Since Claude Code uses a 1 hour prompt cache window for the main agent, if you leave your computer for over an hour then continue a stale session, it's often a full cache miss. To improve this, we have shipped a few…
I wish people would pay more attention to:
* Anthropic is in some way trying to run a business (not a charity) and at least (eventually?) make money and not subsidize usage forever
* "What a steal/good deal" the $100-$200/mo plans are compared to if they had to pay for raw API usage
and less on "how dare you reserve the right to tweak the generous usage patterns you open-ended-ly gave us, we are owed something!"
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#374Hey all, Boris from the Claude Code team here. We've been investigating these reports, and a few of the top issues we've found are: 1. Prompt cache misses when using 1M token context window are expensive. Since Claude Code uses a 1 hour prompt cache window for the main agent, if you leave your computer for over an hour then continue a stale session, it's often a full cache miss. To improve this, we have shipped a few…
Could we get an option to use Opus with a smaller context window? I noticed that results get much worse way earlier than when you reach 1M tokens, and I would love to have a setting so that I could force a compaction at eg 300k tokens.
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#375I'm i alone to think that it become slower that usual to get responses?
Anecdotal, but after playing with the API this week (building a minimal harness for an OS where Claude Code isn't supported), the API felt faster to respond. It did seem like maybe the Max subscriptions are lower priority than API requests. (I hadn't enabled priority service on the API either.)
I don't have metrics, so I could be imagining this, or finally noticing extra lag of the Claude Code client. On the other hand, the API was giving me range anxiety, I won't be pushing a 300k context window into that anytime soon, like I occasionally need to do in Claude Code.
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#376Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#377I skimmed the issue. No wonder Anthropic closes these tickets out without much action. That’s just a wall of AI garbage. Here’s what I’ve done to mostly fix my usage issues: * Turn on max thinking on every session. It save tokens overall because I’m not correcting it of having it waste energy on dead paths. * keep active sessions active. It seems like caches are expiring after ~5 minutes (especially during peak usage…
> This is the most frustrating thing because Anthropic forced the 1M model on everyone.
This is spot on. It would be great (and very easy for them) to have a setting where you can force compaction at a much lower value, eg 300k tokens.
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#378Hey all, Boris from the Claude Code team here. We've been investigating these reports, and a few of the top issues we've found are: 1. Prompt cache misses when using 1M token context window are expensive. Since Claude Code uses a 1 hour prompt cache window for the main agent, if you leave your computer for over an hour then continue a stale session, it's often a full cache miss. To improve this, we have shipped a few…
Could we get an option to use Opus with a smaller context window? I noticed that results get much worse way earlier than when you reach 1M tokens, and I would love to have a setting so that I could force a compaction at eg 300k tokens.
You probably just missed it in his post, but:
"To experiment with this now, try: CLAUDE_CODE_AUTO_COMPACT_WINDOW=400000 claude."
Maybe try changing the 4 to a 3 and see if that works for you?
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#379Earlier quoted context omitted.
Can you clearly state what they messed up?
Not parent but I can guess from watching mostly from the sidelines. They introduced a 1M context model semi-transparently without realizing the effects it would have, then refused to "make it right' to the customer which is a trait most people expect from a business when they spend money on it, specially in the US, and specially when the money spent is often in the thousands of dollars. Unless anthropic has some secr…
Especially since Codex faced the same issue but the team decided to explicitly default to only ~200k context to avoid surprises and degradation for users.
Re: Pro Max 5x quota exhausted in 1.5 hours despite moderate usage
#380Earlier quoted context omitted.
That's weird. Would you mind running /feedback and sharing the id here next time you see this? I'd love to debug
Sure, I really appreciate you looking at this. a6edd0d1-a9ed-4545-b237-cff00f5be090 / https://github.com/anthropics/claude-code/issues/47027 I'm happy to provide any other info that can be useful (as long as i'm not sharing any information about the code or tools we use into a public github issue).
Thank you! Looking