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

API, Claude.ai, and Console services impacted [resolved]

status.anthropic.com

Post reply on HN
Print view View original

41–50 of 81 posts

Re: API, Claude.ai, and Console services impacted [resolved]

#44

Post by adastra22 »

Insanity wrote: post #27
boarush wrote: post #4

Anthropic has by far been the most unreliable provider I've ever seen. Daily incidents, and this one seems to have taken down all their services. Can't even login to the Console.

Maybe they have vibe-coded their own stack! But less tongue-in-cheek, yeah Anthropic definitely has reliability issues. It might be part of trying to move fast to stay ahead of competitors.

They have. Claude Code was their internal dev tool, and it shows.

Re: API, Claude.ai, and Console services impacted [resolved]

#46

Post by clickety_clack »

bdcravens wrote: post #22

Everyone will just have to learn how to do it like we did in the old days, and blindly copy and paste from Stack Overflow.

I don't think that will work for me. I looked for ways to summarize a transcript into a PRD and all I got was "Wow. Incredible. You’ve managed to hit the trifecta: vague, lazy, and entitled. You dump a transcript here and expect the internet to conjure up a polished PRD for you like some kind of corporate fairy godmother? Newsflash: this isn’t Fiverr, and we’re not your underpaid product managers."

Re: API, Claude.ai, and Console services impacted [resolved]

#47

Post by ch4s3 »

clickety_clack wrote: post #46
bdcravens wrote: post #22

Everyone will just have to learn how to do it like we did in the old days, and blindly copy and paste from Stack Overflow.

I don't think that will work for me. I looked for ways to summarize a transcript into a PRD and all I got was "Wow. Incredible. You’ve managed to hit the trifecta: vague, lazy, and entitled. You dump a transcript here and expect the internet to conjure up a polished PRD for you like some kind of corporate fairy godmother? Newsflash: this isn’t Fiverr, and we’re not your underpaid product managers."

You have to prompt with a bad summary.

Re: API, Claude.ai, and Console services impacted [resolved]

#48

Post by CuriouslyC »

adastra22 wrote: post #44
Insanity wrote: post #27

Earlier quoted context omitted.

Maybe they have vibe-coded their own stack! But less tongue-in-cheek, yeah Anthropic definitely has reliability issues. It might be part of trying to move fast to stay ahead of competitors.

They have. Claude Code was their internal dev tool, and it shows.

And yet even dogfooding their own product heavily, it's still a giant janky pile. The prompt work is solid, the focus on optimizing tools was a good insight, and the model makes a good agent, but the actual claude code software is pretty shameful to be the most viable product of a billion dollar company.

Re: API, Claude.ai, and Console services impacted [resolved]

#50

Post by CuriouslyC »

Analemma_ wrote: post #30
Insanity wrote: post #27

Earlier quoted context omitted.

Maybe they have vibe-coded their own stack! But less tongue-in-cheek, yeah Anthropic definitely has reliability issues. It might be part of trying to move fast to stay ahead of competitors.

The tongue-in-cheek jokes are kind of obvious, but even without the snark I think it is worth asking why the supposed 100x productivity boost from Claude Code I keep hearing about hasn't actually resulted in reliability improvements, even from developers who presumably have effectively-unlimited token budgets to spend on improving their stack.

AI gives you what you ask for. If you don't understand your true problems, and you ask it to solve the wrong problems, it doesn't matter how much compute you burn, you're still gonna fail.
Post reply on HN