381–390 of 695 posts
Earlier quoted context omitted.
We are taking it seriously, and are continuing to investigate. We are not trusting the metrics.
[flagged]
Thank you Boris.
Earlier quoted context omitted.
Man, expecting the minimal from companies who are supposed to deliver a pro... there is no SLA for any this, so you are right. Also, why is there no SLA?
Because this is ultimately a beta service. The whole industry is.
Hey 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 don't want a nudge. I want a clear RED WARNING with "You've gone away from your computer a bit too long and chatted too much at the coffee machine. You're better off starting a new context!"
Hey 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…
How can we turn of 1m context? I don't find it has ever helped.
"CLAUDE_CODE_AUTO_COMPACT_WINDOW=400000"
Hey 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!"
Earlier quoted context omitted.
That might be, but the argument was that poor cache utilization was costing Anthropic too much money in other harnesses. If cache is considered in rate limits, it doesn’t matter from a cost perspective, you’ll just hit your rate limits faster in other harnesses that don’t try to cache optimize.
There were two issues with some other 3p harnesses: 1. Poor cache utilization. I put up a few PRs to fix these in OpenClaw, but the problem is their users update to new versions very slowly, so the vast majority of requests continued to use cache inefficiently. 2. Spiky traffic. A number of these harnesses use un-jittered cron, straining services due to weird traffic shape. Same problem -- it's patched, but users upg…
For me, iterating with Claude begins to degrade at 200k context used, by 350k it’s crossed-fingers time, by 500k it’s essentially useless. Starting a fresh context after 300k is usually the best move imho. I wonder if people are hitting a case where Claude becomes both dumb and increasingly more expensive, essentially a doom loop.
I'm using another tool, not claude code, but I don't think that matters much.
Hey 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 think this may be the biggest concern for people building tools on the API: https://github.com/anthropics/claude-code/issues/46829
I would argue that KV caching is a net gain for Ant and a well-maintained cache is the biggest thing that can generate induced demand and a thriving third party ecosystem. https://safebots.ai/papers/KV.pdf
Yet, there must obviously be something different for so many people to be reporting these issues.
I feel for the Anthropic devs that have to deal with this, having to figure out what setup everyone has, what their usage patterns are to filter out the valid reports, and then also deal with the backlash from people that were just pulling obvious footguns like having a ton of skills/MCPs polluting their context window.
Earlier quoted context omitted.
I don't want a nudge. I want a clear RED WARNING with "You've gone away from your computer a bit too long and chatted too much at the coffee machine. You're better off starting a new context!"
Why is nobody even asking why that should be an issue? No other text editor shits the bed that way. The whole point of the computer is that it patiently waits for my input.