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

Claude: Elevated errors across many models [resolved]

status.claude.com

Post reply on HN
Print view View original

161–170 of 173 posts

Re: Claude: Elevated errors across many models [resolved]

#161

Post by spondyl »

evilturnip wrote: post #13

I do feel like for all their dogfooding of AI coding, their own software/APIs are quite buggy and work against their message. Claude Code is especially buggy in windows terminal. The rendering is quite slow, choppy and lines frequently get garbled. In contrast, using antigravity cli is the exact opposite: fast, smooth and very responsive.

> their own software/APIs are quite buggy

Our org has been attempting to trial Fast Mode on and off but enabling it in Claude Code just says something like "not available with your cloud provider"

It turns out that for all of the matrices on the documentation site, there is a secret "other" set of infrastructure for those who bill Enterprise via AWS Marketplace where certain features like Fast Mode are incompatible when using "aws routing"

Anthropic Support straight up mentioned that Claude Code just doesn't handle this case correctly and erroneously gives you the impression that it's supported against your billing method, and that it's all effectively undocumented.

I suppose this means there are like 5 different AWS methods of use:

- Bedrock (Legacy)

- Bedrock

- Claude for AWS

- Claude via Marketplace

- Anthropic's own "primary infrastructure"

and then roll in other cloud provider variations

On that note, I recall Datadog having coupled billing and infrastructure per cloud (ie; billing via GCP requires using the GCP infra) and was wondering if commenters had any insights into if there is some special requirement/complexity around marketplace billing for cloud providers or if it's just some weird design choice?

Re: Claude: Elevated errors across many models [resolved]

#162

Post by redox99 »

wxw wrote: post #21

I’ve been using Codex w GPT 5.5 more than Claude Code recently. I think Anthropic won the marketing game because Codex is quite good, even better IME.

Claude has always been better at making pretty frontends, which is crucial for people that vibecode entire apps in a couple of prompts. And that people drive a lot of the hype.

Codex ever since ~5.2 has been better at long tasks in large codebases.

Re: Claude: Elevated errors across many models [resolved]

#163

Post by kowbell »

pixelpoet wrote: post #102
crystal_revenge wrote: post #86

Earlier quoted context omitted.

> in windows terminal This is an aside, but I'm really struck by how many people on HN use Windows (based on repeated mentions I've seen in comments). I've worked for a pretty wide range of companies over the last decade and only one, maybe two companies even had any people that worked on Windows machines. I haven't worked at a company where devs used Windows in 15 years (and even that company eventually switched to…

While we're doing anecdotes: I essentially never meet people who own an iPhone, and I've lived (3 months+) in a huge number of countries and cities. The handful people who do are American; bubbles exist :) For a long time, high end graphics and games was mainly done on Windows and Visual Studio. I'm from that world, and only made the Linux transition last year November after Microsoft forced everyone's hand.

> For a long time, high end graphics and games was mainly done on Windows and Visual Studio.

This implies games are not still mainly done on Windows, which they absolutely are!

Re: Claude: Elevated errors across many models [resolved]

#164

Post by nilkn »

crystal_revenge wrote: post #86
evilturnip wrote: post #13

I do feel like for all their dogfooding of AI coding, their own software/APIs are quite buggy and work against their message. Claude Code is especially buggy in windows terminal. The rendering is quite slow, choppy and lines frequently get garbled. In contrast, using antigravity cli is the exact opposite: fast, smooth and very responsive.

> in windows terminal This is an aside, but I'm really struck by how many people on HN use Windows (based on repeated mentions I've seen in comments). I've worked for a pretty wide range of companies over the last decade and only one, maybe two companies even had any people that worked on Windows machines. I haven't worked at a company where devs used Windows in 15 years (and even that company eventually switched to…

I use Windows on my home PC simply because it's such a versatile setup thanks to native GPU support, game support, and WSL2. It feels like I can do almost everything on one machine with little to no compromise. If I didn't care about games I'd probably load Linux onto it, but WSL2 gets me most of what I want from both worlds without needing to do that.

Re: Claude: Elevated errors across many models [resolved]

#165

Post by Atotalnoob »

crystal_revenge wrote: post #86
evilturnip wrote: post #13

I do feel like for all their dogfooding of AI coding, their own software/APIs are quite buggy and work against their message. Claude Code is especially buggy in windows terminal. The rendering is quite slow, choppy and lines frequently get garbled. In contrast, using antigravity cli is the exact opposite: fast, smooth and very responsive.

> in windows terminal This is an aside, but I'm really struck by how many people on HN use Windows (based on repeated mentions I've seen in comments). I've worked for a pretty wide range of companies over the last decade and only one, maybe two companies even had any people that worked on Windows machines. I haven't worked at a company where devs used Windows in 15 years (and even that company eventually switched to…

I just started at a new company who gave me a Mac to work on windows apps.

Re: Claude: Elevated errors across many models [resolved]

#166

Post by Raj_Sidwadkar »

evilturnip wrote: post #13

I do feel like for all their dogfooding of AI coding, their own software/APIs are quite buggy and work against their message. Claude Code is especially buggy in windows terminal. The rendering is quite slow, choppy and lines frequently get garbled. In contrast, using antigravity cli is the exact opposite: fast, smooth and very responsive.

100%,I have used it for two of my projects. One prompt for fixing one issue triggers other 10 npm, lint errors which you have already solved in the previous sprint.

It takes hours to manhunt these errors and also you cannot risk again to tell the local llm to fix it.

Re: Claude: Elevated errors across many models [resolved]

#167

Post by mdavid626 »

CharlesW wrote: post #61
mdavid626 wrote: post #44

Earlier quoted context omitted.

Or pi.dev - also super fast and simple. Claude Code is sluggish, buggy, slow. Typical big enterprise garbage. The only good thing at Anthropic are the models.

Claude Code is notably better than Pi, although I wish them the best of luck in their efforts. As https://c-daniele.github.io/en/posts/2026-05-18-coding-harne... notes, "Pi's lightness comes from a default setup that does not survive contact with reality." The same post on Claude Code: "Even though the System Prompt and tool descriptions are clearly more verbose, most of the extra tokens encode product features and r…

What are you talking about?

Did you even use pi.dev?

I used them both and I can tell you there isn’t a single feature what pi.dev misses from Claude Code.

Re: Claude: Elevated errors across many models [resolved]

#168

Post by comboy »

sunaookami wrote: post #43
evilturnip wrote: post #13

I do feel like for all their dogfooding of AI coding, their own software/APIs are quite buggy and work against their message. Claude Code is especially buggy in windows terminal. The rendering is quite slow, choppy and lines frequently get garbled. In contrast, using antigravity cli is the exact opposite: fast, smooth and very responsive.

Have you tried out the new fullscreen renderer with /tui ?

What's that about? It's full screen/terminal anyway. Is it just switching some rendering engine under the hood?

Re: Claude: Elevated errors across many models [resolved]

#169

Post by B1FF_PSUVM »

alephnerd wrote: post #136
computerex wrote: post #105

Earlier quoted context omitted.

Maybe hackernews has older crowd. Windows was the defacto developer OS for a very long time.

HN definitely has an older crowd, but additionally I've noticed HN is increasingly dominated by Europeans from 5am-2pm PST. "American" HN seems to kick off around 3pm-10pm PST now. Even the HN dataset on HuggingFace shows that most engagement on HN is now during non-US hours [0] and drops off as Europe goes to sleep. [0] - https://huggingface.co/datasets/open-index/hacker-news

> Europeans from 5am-2pm PST

Well, the EU is putting the kibosh on that PDQ. The precious stays at home.

Re: Claude: Elevated errors across many models [resolved]

#170

Post by antupis »

black_knight wrote: post #152
orphea wrote: post #65

Earlier quoted context omitted.

Dunno, I prefer GPT 5.5 too for the same reasons as the parent. Extremely subjective but had better results with it too. Maybe I just got unlucky with Claude a few times, but even the latest Opus was dumb .

Fascinating how people have such complete diametrically opposed experiences. I guess both models have it in them to behave very differently in different circumstances and we have very little idea what pushes them in this or that direction. I guess it does boil down to luck! Personally, Claude Opus (and in the few interactions I had with it, Fable) has been the far the superior experience. GPT-5.5 seems dumber and mor…

It might be harness or prompting style. Personally I use opencode and my prompting style is very plain and terse . Where tasks are very small. Opus and Sonet too often are too verbose and go tangent. Where GPT5.5 is much stricter.
Post reply on HN