Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

An update on recent Claude Code quality reports

anthropic.com

Post reply on HN
Print view View original

371–380 of 778 posts

Re: An update on recent Claude Code quality reports

#371

Post by kccqzy »

bcherny wrote: post #124
6keZbCECT2uB wrote: post #61

"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…

This just does not match my workflow when I work on low-priority projects, especially personal projects when I do them for fun instead of being paid to do them. With life getting busy, I may only have half an hour each night with Claude to make some progress on it before having to pause and come back the next day. It’s just the nature of doing personal projects as a middle-aged person.

The above workflow basically doesn’t hit the rate limit. So I’d appreciate a way to turn off this feature.

Re: An update on recent Claude Code quality reports

#372

Post by cmrdporcupine »

slashdave wrote: post #369
MrOrelliOReilly wrote: post #317

IMO this is the consequence of a relentless focus on feature development over core product refinement. I often have the impression that Anthropic would benefit from a few senior product people. Someone needs to lend them a copy of “Escaping the Build Trap.” Just because we _can_ rapidly add features now doesn’t mean we should. PS I’m not referencing a well-known book to suggest the solution is trite product group thi…

They need to keep up with demand, because compute resources are clearly limited. That means they have no choice but to add these features, or things break, or they have to stop taking new customers. All of those options are unacceptable.

They're losing customers because of quality concerns. Pausing development and focusing 100% on quality is how you fix that.

That said, that may not have been obvious at all in the Jan/Feb time frame when they got a wave of customers due to ethical concerns.

Re: An update on recent Claude Code quality reports

#373

Post by slashdave »

nickdothutton wrote: post #130

I presume they don't yet have a cohesive monetization strategy, and this is why there is such huge variability in results on a weekly basis. It appears that Anthropic are skipping from one "experiment" to another. As users we only get to see the visible part (the results). Can't design a UI that indicates the software is thinking vs frozen? Does anyone actually believe that?

Compute is limited worldwide. No amount of money can make these compute platforms appear overnight. They are buying time because the only other option is to stop accepting customers.

Re: An update on recent Claude Code quality reports

#374

Post by dicethrowaway1 »

northern-lights wrote: post #328
dicethrowaway1 wrote: post #211

Earlier quoted context omitted.

Maybe they could let users store an encrypted copy of the cache? Since the users wouldn't have Anthropic's keys, it wouldn't leak any information about the model (beyond perhaps its number of parameters judging by the size).

Encryption can only ensure the confidentiality of a message from a non-trusted third party but when that non-trusted third party happens to be your own machine hosting Claude Code, then it is pointless. You can always dump the keys (from your memory) that were used to encrypt/decrypt the message and use it to reconstruct the model weights (from the dump of your memory).

jetbalsa said that the cache is on Anthropic's server, so the encryption and decryption would be server-side. You'd never see the encryption key, Anthropic would just give you an encrypted dump of the cache that would otherwise live on its server, and then decrypt with their own key when you replay the copy.

Re: An update on recent Claude Code quality reports

#375

Post by kamranjon »

This black box approach that large frontier labs have adopted is going to drive people away. To change fundamental behavior like this without notifying them, and only retroactively explaining what happened, is the reason they will move to self-hosting their own models. You can't build pipelines, workflows and products on a base that is just randomly shifting beneath you.

Re: An update on recent Claude Code quality reports

#376

Post by abtinf »

bcherny wrote: post #126
bauerd wrote: post #98

>On March 4, we changed Claude Code's default reasoning effort from high to medium to reduce the very long latency—enough to make the UI appear frozen—some users were seeing in high mode Instead of fixing the UI they lowered the default reasoning effort parameter from high to medium? And they "traced this back" because they "take reports about degradation very seriously"? Extremely hard to give them the benefit of do…

Hey, Boris from the team here. We did both -- we did a number of UI iterations (eg. improving thinking loading states, making it more clear how many tokens are being downloaded, etc.). But we also reduced the default effort level after evals and dogfooding. The latter was not the right decision, so we rolled it back after finding that UX iterations were insufficient (people didn't understand to use /effort to increas…

You didn’t anticipate most people stick with defaults?

Re: An update on recent Claude Code quality reports

#377

Post by cageface »

carlgreene wrote: post #73
mannanj wrote: post #15

Earlier quoted context omitted.

so who do you trust and go to? (NotClearlySo)OpenAI?

I "subconsciously" moved to codex back in mid Feb from CC and it's been so freaking awesome. I don't think it's as good at UI, but man is it thorough and able to gather the right context to find solutions. I use "subconsciously" in quotes because I don't remember exactly why I did it, but it aligns with the degradation of their service so it feels like that probably has something to do with it even though I didn't re…

Codex does better if you ask it to take screenshots and critique its own UI work and iterate. It rarely one-shots something I like but it can get there in steps.

Re: An update on recent Claude Code quality reports

#378

Post by CamperBob2 »

marcyb5st wrote: post #108
xlayn wrote: post #19

If anthropic is doing this as a result of "optimizations" they need to stop doing that and raise the price. The other thing, there should be a way to test a model and validate that the model is answering exactly the same each time. I have experienced twice... when a new model is going to come out... the quality of the top dog one starts going down... and bam.. the new model is so good.... like the previous one 3 mont…

Apart from Anthropic nobody knows how much the average user costs them. However the consensus is "much more than that". If they have to raise prices to stop hemorrhaging money, would you be willing to pay 1000 bucks a month for a max plan? Or 100$ per 1M pitput tokens (playing numberWang here, but the point stands). If I have to guess they are trying to get balance sheet in order for an IPO and they basically have 3…

$1000/mo for guaranteed functionality >= Opus 4.6 at its peak? Yes, I'd probably grumble a bit and then whip out the credit card.

I'm not a heavy LLM user, and I've never come anywhere the $200/month plan limits I'm already subscribed to. But when I do use it, I want the smartest, most relentless model available, operating at the highest performance level possible.

Charge what it takes to deliver that, and I'll probably pay it. But you can damned well run your A/B tests on somebody else.

Re: An update on recent Claude Code quality reports

#379

Post by zem »

ugh, caching based on idle time is horrible for my usage anyway; since claude is both fairly slow and doesn't really have much of a daily quota anyway I often tell it to do something and then wander off and come back to check on it when I next think about it. I always vaguely assumed that my session would not "detect" the intervening time anyway since it was all async. I guess from a global perspective time-based cache eviction makes sense.

Re: An update on recent Claude Code quality reports

#380

Post by arcza »

bcherny wrote: post #124
6keZbCECT2uB wrote: post #61

"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…

You need to seriously look at your corporate communications and hire some adults to standarise your messaging, comms and signals. The volatility behind your doors is obvious to us and you'd impress us much more if you slowed down, took a moment to think about your customers and sent a consistent message.

You lost huge trust with the A/B sham test. You lost trust with enshittification of the tokenizer on 4.6 to 4.7. Why not just say "hey, due to huge input prices in energy, GPU demand and compute constraints we've had to increase Pro from $20 to $30." You might lose 5% of customers. But the shady A/B thing and dodgy tokenizer increasing burn rate tells everyone inc. enterprise that you don't care about honesty and integrity in your product.

I hope this feedback helps because you still stand to make an awesome product. Just show a little more professionalism.

Post reply on HN