Whatever they did, with the max plan, my daily usage quota was consumed in less than 10 minutes. Weird, let's hope they fix the usage now.
An update on recent Claude Code quality reports
531–540 of 778 posts
Re: An update on recent Claude Code quality reports
#532My hypothesis is that some of this a perceived quality drop due to "luck of the draw" where it comes to the non-deterministic nature of VM output. A couple weeks ago, I wanted Claude to write a low-stakes personal productivity app for me. I wrote an essay describing how I wanted it to behave and I told Claude pretty much, "Write an implementation plan for this." The first iteration was _beautiful_ and was everything…
I also think some of this stems from the default 1m context window. Performance starts to degrade when context size increases, and each token over (i think the level is) 400k counts more towards your usage limit. Defaulting to 1m context size, if people arent carefully managing context (which they shouldnt ever have to in an ideal world), they would notice somewhat degraded performance and increased token usage regardless.
Re: An update on recent Claude Code quality reports
#533Are they also going to refund all the extra usage api $$$ people spent in the last month? Also I don’t know how “improving our Code Review tool” is going to improve things going forward, two of the major issues were intentional choices. No code review is going to tell them to stop making poor and compromising decisions.
I stopped using it for nearly a month because of the performance degradation. I paid for the whole month. Wasted money.
Re: An update on recent Claude Code quality reports
#534Earlier quoted context omitted.
No? It's not because it's a cache, it's because they're scared of letting you see the thinking trace. If you got the trace you could just send it back in full when it got evicted from the cache. This is how open weight models work.
The trace goes back fine, that's not the issue. The issue is that if they send the full trace back, it will have to be processed from the start if the cache expired, and doing that will cause a huge one-time hit against your token limit if the session has grown large. So what Boris talked about is stripping things out of the trace that goes back to regenerate the session if the cache expires. Doing this would help av…
>and doing that will cause a huge one-time hit against your token limit if the session has grown large.
Anthropic already profited from generating those tokens. They can afford subsidize reloading context.
Re: An update on recent Claude Code quality reports
#535"On March 26, we shipped a change to clear Claude's older thinking from sessions that had been idle for over an hour, to reduce latency when users resumed those sessions. A bug caused this to keep happening every turn for the rest of the session instead of just once, which made Claude seem forgetful and repetitive. We fixed it on April 10. This affected Sonnet 4.6 and Opus 4.6" This makes no sense to me. I often leav…
Hey, Boris from the Claude Code team here. Normally, when you have a conversation with Claude Code, if your convo has N messages, then (N-1) messages hit prompt cache -- everything but the latest message. The challenge is: when you let a session idle for >1 hour, when you come back to it and send a prompt, it will be a full cache miss, all N messages. We noticed that this corner case led to outsized token costs for u…
Hi, thanks for Claude Code. I was wondering though if you'd considering adding a mode to make text green and characters come down from the top of the screen individually, like in The Matrix?
Re: An update on recent Claude Code quality reports
#536Earlier quoted context omitted.
Hey, Boris from the Claude Code team here. Normally, when you have a conversation with Claude Code, if your convo has N messages, then (N-1) messages hit prompt cache -- everything but the latest message. The challenge is: when you let a session idle for >1 hour, when you come back to it and send a prompt, it will be a full cache miss, all N messages. We noticed that this corner case led to outsized token costs for u…
Resuming sessions after more than 1 hour is a very common workflow that many teams are following. It will be great if this is considered as an expected behaviour and design the UX around it. Perhaps you are not realising the fact that Claude code has replaced the shells people were using (ie now bash is replaced with a Claude code session).
> Resuming sessions after more than 1 hour is a very common workflow that many teams are following
Yeah it's called lunch!
Re: An update on recent Claude Code quality reports
#537Anthropic releases used to feel thorough and well done, with the models feeling immaculately polished. It felt like using a premium product, and it never felt like they were racing to keep up with the news cycle, or reply to competitors. Recently that immaculately polished feel is harder to find. It coincides with the daily releases of CC, Desktop App, unknown/undocumented changes to the various harnesses used in CC/…
Boris from the Claude Code team here. We agree, and will be spending the next few weeks increasing our investment in polish, quality, and reliability. Please keep the feedback coming.
Can you please fix https://github.com/anthropics/claude-code/issues/43713 ?
Re: An update on recent Claude Code quality reports
#538Earlier quoted context omitted.
Is Gemini cli not an agentic model? Or are you just saying it's built poorly? Gemini 2.5 didn't really work for me but Gemini 3 seems fairly solid
Gemini fairs poorly at tool use, even in its own CLI and even in Antigravity. It gets into a mess just editing source files, it's tragic because it's actually not a bad model otherwise.
It frequently fails to apply its diffs at first but it always succeeds eventually for me. I'm happy with it. I understand it is slower than other models but it also costs barely anything per month.
Re: An update on recent Claude Code quality reports
#539Earlier quoted context omitted.
> Claude Code abstracts the API, so it should abstract this behavior as well, or educate the user about it. Does mmap(2) educate the developer on how disk I/O works? At some point you have to know something about the technology you're using, or accept that you're a consumer of the ever-shifting general best practice, shifting with it as the best practice shifts.
Does using print() in Python means I need to understand the Kernel? This is an absurd thought.
That might be an absurd comparison, but we can fix that.
If you were being charged per character, or running down character limits, and printing on printers that were shared and had economic costs for stalled and started print runs, then:
You wouldn’t “need” to understand. The prints would complete regardless. But you might want to. Personal preference.
Which is true of this issue to.
Re: An update on recent Claude Code quality reports
#540Just add this, it works better than Opus 4.7
vim ~/.claude/settings.json
{ "model": "claude-opus-4-6", "fastMode": false, "effortLevel": "high", "alwaysThinkingEnabled": true, "autoCompactWindow": 700000 }