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

281–290 of 293 posts

Re: Elevated error rate across multiple models

#281

Post by spiderfarmer »

armdave wrote: post #58
maccard wrote: post #23

Earlier quoted context omitted.

When that downtime happens is way more important than the amount of it. Imagine if your payroll system was down for 8 hours a month, but it just so happened to be the day payroll do their calculations?

Totally. The uptime metrics are deceiving imo. A more useful measure for a productivity tool like Claude Code is uptime during work hours for a given time zone. I strongly suspect at least for the three US time zones, we would be looking at a single nine of uptime for that measure.

Imagine your boss complaining about your productivity in the same way you blame your tools.

Re: Elevated error rate across multiple models

#282

Post by mik3y »

tovej wrote: post #273
mik3y wrote: post #267

Earlier quoted context omitted.

Bad faith, or perhaps just ignorance. It reminds me of purist junior engineers - and I have been one - refusing to understand or tradeoff in the world beyond their own. Rather than argue with those of us who are pointing out messy realities, this commenter might be better served filing a bug against any number of the projects that offer installation this way, asking them to remove it, and see if it lands any better.…

I would appreciate it if you would respond to me directly rather than suggest vaguely that I'm inexperienced and don't understand the realities of software distribution. I would also appreciate it if you actually talk about something concrete rather than simply claiming to be right. You shouldn't pipe stuff from the internet into your shell. Are you claiming that's about some highfallutin "technical purity"? Is it te…

Sure: I think you're essentially missing a whole set of concerns - ones that are not purely technical - behind why this method is popular; and so your arguments wouldn't convince someone actually responsible for one of these scripts to change or cease the practice.

Nobody would argue that it's categorically safe/good/smart to blindly pipe a script into your shell; and for the record, I agree. I would also readily agree that habituating users to doing this probably creates new, more general risks especially among how less-technical users interact with their CLI.

However, the realities of the "real world" make it popular for a reason, in light of those negatives; tons of scaled projects continue to offer a 1-liner. So we have to ask, why? They'd probably say that's because it (a) improves project adoption, and (b) reduces "install broken" tickets.

You have to address the non-technical merits and goals to get behavior to change here, and sadly, I don't think anyone has done that.

But who cares about me? I'm not currently maintaining one of these (though I did once). My suggestion to bring your argument to an active project was genuine: try it! I'd be delighted to see you bring about the change you want.

[PS: The commenter I replied to originally used the term "bad faith", which they've since edited]

Re: Elevated error rate across multiple models

#283

Post by gaiagraphia »

nsvd2 wrote: post #231
gaiagraphia wrote: post #26

[flagged]

If the government wanted people to take holidays off they could just legislate that people can't work on those days. I doubt there is any political will to do this, though.

Is it that simple when everybody is trying to promptmax foreign models?

Re: Elevated error rate across multiple models

#284

Post by maccard »

spiderfarmer wrote: post #281
armdave wrote: post #58

Earlier quoted context omitted.

Totally. The uptime metrics are deceiving imo. A more useful measure for a productivity tool like Claude Code is uptime during work hours for a given time zone. I strongly suspect at least for the three US time zones, we would be looking at a single nine of uptime for that measure.

Imagine your boss complaining about your productivity in the same way you blame your tools.

Imagine you told your boss you slept 8 hours a day like everyone else, so your productivity is the same. Except you sleep during working hours and everyone else is awake!

Re: Elevated error rate across multiple models

#285

Post by root-parent »

Schiendelman wrote: post #223
root-parent wrote: post #48

Earlier quoted context omitted.

>> It’s 36°C outside Yeah AI Data Centers do that....

I really wish people wouldn't pretend these actually matter compared to, say, the proliferation of personal internal combustion cars, or shipping using bunker fuel.

And I really wish HN users would stop considering itself a temporarily embarrassed billionaire and stop being a chill for VCs...

[1] - "...Data centers are projected to surge from consuming 4% of U.S. power to 9%–12% by 2030. Morgan Stanley forecasts that the resulting emissions from this American infrastructure spike will equal roughly 40% of the entire U.S..."

[1] - https://opportunitygreen.org/data-centres/?tab=overview

Re: Elevated error rate across multiple models

#286

Post by root-parent »

throwaw12 wrote: post #81
root-parent wrote: post #41

Earlier quoted context omitted.

>> What can your company do? Hire some Developers?

Developers who can code without LLMs will go extinct in couple years and there will be legends about them, you should at least have some decent open weight model as a backup

From everybody will learn to code to ...nobody will know how to code...

Re: Elevated error rate across multiple models

#287

Post by spiderfarmer »

maccard wrote: post #284
spiderfarmer wrote: post #281

Earlier quoted context omitted.

Imagine your boss complaining about your productivity in the same way you blame your tools.

Imagine you told your boss you slept 8 hours a day like everyone else, so your productivity is the same. Except you sleep during working hours and everyone else is awake!

Yeah, because sleep is the only unproductive thing you can do during working hours.

Re: Elevated error rate across multiple models

#288

Post by bel8 »

thejazzman wrote: post #278
yanis_t wrote: post #18

I suppose it's a good time to encourage people trying out pi[1] with any cheap model from the openrouter rankings page[1]. [1] https://pi.dev/ [2] https://openrouter.ai/rankings

I retried Pi yesterday with GLM5.2 and Deepseek I asked a simple question about my codebase. Pi: >60s and 100k tokens, I cancelled and gave up Claude (pointed at the same deepseek model): 17s 15k tokens I burned my $5 GLM budget in 15 minutes. So idk what the Pi hype is about cuz this is my 3rd disappointing try

GLM 5.2 is priced at 1/3 of Opus. Depending on who you ask for a napkin math.

Not worth it in my opinion.

You'll get 10x more value by using MiMo 2.5 or DeepSeek Flash which is what I use for most code.

Re: Elevated error rate across multiple models

#289

Post by tovej »

qarl2 wrote: post #280
tovej wrote: post #245

Earlier quoted context omitted.

99% of developers are most definitely not comfortable piping a script into the shell. I would never runa script without reviewing it. I would install a package from a distros repository without reviewing the contents, however, because I can trust that a distro maintainer has reviewed it, that anyone else in the community can review it, and that that the bytes I'm downloading are the specific bytes I'm supposed to be…

As someone who has spent years in the software industry in silicon valley - My experience does not match yours.

I didn't realize silicon valley was full of software cowboys.

Well, I suppose that matches the "move fast and break things" credo. lol.

Re: Elevated error rate across multiple models

#290

Post by Ferret7446 »

agentcooper wrote: post #263
yanis_t wrote: post #18

I suppose it's a good time to encourage people trying out pi[1] with any cheap model from the openrouter rankings page[1]. [1] https://pi.dev/ [2] https://openrouter.ai/rankings

With Agent Client Protocol (ACP) you can keep the same UI and switch not models, but entire agents, that means using tools/prompts/compaction/etc that are tailored for the model. Try Zed[1] for GUI and pool[2] for TUI. [1] https://zed.dev/ [2] https://github.com/poolsideai/pool

I tried ACP but the UI for agents is so minimal I don't see much of a point. They're all just text boxes now.
Post reply on HN