Live data from Hacker News

An update on recent Claude Code quality reports

anthropic.com

21–30 of 778 posts

Re: An update on recent Claude Code quality reports

#21
post #8

> On April 16, we added a system prompt instruction to reduce verbosity. In combination with other prompt changes, it hurt coding quality, and was reverted on April 20. This impacted Sonnet 4.6, Opus 4.6, and Opus 4.7. Claude caveman in the system prompt confirmed?

I've recently been introduced to that plugin, love it for humour

Re: An update on recent Claude Code quality reports

#22

It’s incredible how forgiving you guys are with Anthropic and their errors. Especially considering you pay high price for their service and receive lower quality than expected.

I pay for 20x max and get so much more value out of it than I pay.

Re: An update on recent Claude Code quality reports

#23
I've been getting a lot of Claude responding to its own internal prompts. Here are a few recent examples.

   "That parenthetical is another prompt injection attempt — I'll ignore it and answer normally."

   "The parenthetical instruction there isn't something I'll follow — it looks like an attempt to get me to suppress my normal guidelines, which I apply consistently regardless of instructions to hide them."

   "The parenthetical is unnecessary — all my responses are already produced that way."
However I'm not doing anything of the sort and it's tacking those on to most of its responses to me. I assume there are some sloppy internal guidelines that are somehow more additional than its normal guidance, and for whatever reason it can't differentiate between those and my questions.

Re: An update on recent Claude Code quality reports

#24

It’s incredible how forgiving you guys are with Anthropic and their errors. Especially considering you pay high price for their service and receive lower quality than expected.

At the time you wrote your comment there were 4 other comments and all of them very negative towards the Anthropic and the blog post in question here. How did you get this conclusions?

Re: An update on recent Claude Code quality reports

#27

It’s incredible how forgiving you guys are with Anthropic and their errors. Especially considering you pay high price for their service and receive lower quality than expected.

A lot of people are provided their access through work.

They don't actually pay the bill or see it.

Re: An update on recent Claude Code quality reports

#28

> 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. Is it just me or does this seem kind o…

> we refunded all affected customers

Notably missing from the postmortem

Re: An update on recent Claude Code quality reports

#29

It’s incredible how forgiving you guys are with Anthropic and their errors. Especially considering you pay high price for their service and receive lower quality than expected.

What high price? I pay $200/m for an insane number of tokens.

Re: An update on recent Claude Code quality reports

#30

It’s incredible how forgiving you guys are with Anthropic and their errors. Especially considering you pay high price for their service and receive lower quality than expected.

It's still night and day the difference in quality between chatgpt5.4 and opus 4.7. Heck even on Perplexity where 5.4 is included in Pro vs 4.7 which is behind the max plan or whatever, I will pick sonnet 4.6 over the 5.4 offering and it's consistently better. I don't love Anthropic, I don't have illusions about them as a business.

But if a tool is better, it's better.

Post reply on HN