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

Elevated error rate across multiple models

status.claude.com

Post reply on HN
Print view View original

131–140 of 293 posts

Re: Elevated error rate across multiple models

#131

Post by hgoel »

throwaway2027 wrote: post #28
iLemming wrote: post #13

Goddamit, like losing the ability for coding without any Internet wasn't enough, now I have to forget how to code without Claude? ps. if you say you still capable of developing software without the Internet, you're lying. Perhaps, to your own self.

I'm perfectly capable of programming without internet or AI but I would admit it would take longer and in the modern world we live in it's often not economical to do so. After programming for over 20 years you start to get in that flow automatically at least you used to do so. I don't know if people starting out to program will be able to, but most experienced developers will feel this way I assume.

It depends on the language but agreed. If I didn't have internet or AI access, I'd still be able to pull out manpages or dig into source code.

I wouldn't like it and it'd be slower, but I still understand my environment in sufficient depth to work without external info if I absolutely have to. Even with AI, once in a while I ask it to just give me some hints instead of solving something for me, so I'm forced to do the work.

Re: Elevated error rate across multiple models

#132

Post by tomasphan »

stevemk14ebr wrote: post #70
tomasphan wrote: post #53

I request an official statement from Anthropic explaining how they're going to limit outages in the future. Elevated errors almost always means its down for me and I can't be that unlucky statistically speaking. It seems that Anthropic does not have a good grip on the ops side of things.

I'm sure they'll get right on that for ya bud

Thanks for your contribution to this problem. Keen to see what you come up with next!

Re: Elevated error rate across multiple models

#133

Post by arbll »

tovej wrote: post #98
mik3y wrote: post #59

Earlier quoted context omitted.

I am genuinely curious what it tells you, as "curl https//.. | sh" has long been an enormously popular approach to distribution in the open source world. Homebrew, to name just one example, advertises a similar method. (pi.sh also documents other install methods, like `npm`, on their homepage) If trust and security is the issue, unfortunately "better" ideas like hashpipe [1] never achieved critical mass [1] https://n…

What about better ideas like installing from source, or using a package manager? Or even flatpaks.

From source: creates much more work for the user.

Package managers: ecosystem is fragmented, requiring a long list of distro- and package-manager-specific instructions. Many scripts already install through package managers, they simply make the user’s life easier.

Flatpaks: These are clearly designed for desktop applications, with CLIs treated as an afterthought. They may be the best long-term hope, but today they are definitely not as convenient or widely available as a simple script.

If you care about adoption, `curl | sh` is the only real option today, which is why virtually all project show it as the first option.

Re: Elevated error rate across multiple models

#134

Post by dakiol »

dpedu wrote: post #60
halfmatthalfcat wrote: post #6

Incredible how we can claim productivity increases when its either Claude or Github shitting the bed every other day. It must even itself out to a net neutral gain in the long term.

I don't understand this comment. At worst, we're just back to the baseline - working without AI help.

The bunch of MD files in the codebase is becoming "tech" debt. It's just English prose, sure, but thousands of lines of English prose. Terse. Succinct. Difficult (if not impossible) to maintain manually without LLMs. That's not "baseline"

Re: Elevated error rate across multiple models

#135

Post by MattGaiser »

MontyCarloHall wrote: post #92

I don’t prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops. — Boris Cherny, head of Claude Code Reliability is a direct reflection of the quality of the underlying infrastructural code. If even Anthropic, the company with the world's best agentic vibecoders, has horribly unreliable infrastructure, it really says something about the quality of the world…

On the other hand we are also willing to buy it, so reliability is arguably not as valued a good as people assumed.

Re: Elevated error rate across multiple models

#136

Post by qsxfthnkp2322 »

dsmurrell wrote: post #101
MontyCarloHall wrote: post #92

I don’t prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops. — Boris Cherny, head of Claude Code Reliability is a direct reflection of the quality of the underlying infrastructural code. If even Anthropic, the company with the world's best agentic vibecoders, has horribly unreliable infrastructure, it really says something about the quality of the world…

I wonder how they fix things when Claude is down.

lol probably use their dev or qa Claude environment to fix prod

Re: Elevated error rate across multiple models

#139

Post by dpedu »

dakiol wrote: post #134
dpedu wrote: post #60

Earlier quoted context omitted.

I don't understand this comment. At worst, we're just back to the baseline - working without AI help.

The bunch of MD files in the codebase is becoming "tech" debt. It's just English prose, sure, but thousands of lines of English prose. Terse. Succinct. Difficult (if not impossible) to maintain manually without LLMs. That's not "baseline"

Developers having a troubled relationship with documentation isn't new.
Post reply on HN