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

Claude now has access to a server-side container environment

anthropic.com

Post reply on HN
Print view View original

341–350 of 363 posts

Re: Claude now has access to a server-side container environment

#341

Post by mkw2000 »

atonse wrote: post #338
ranguna wrote: post #311

Earlier quoted context omitted.

That's not what the op asked. They didn't ask whether claude is useful in general, they asked whether it was good compared to other LLMs. On of the tricks to a healthy discussions is to actually read/listen to what the other side is trying to say. Without that, you're just talking to yourself.

If my tone came off as confrontational, that was not my intent. But I do intend to say this: It seems to me that _you_ are ascribing malice to my comment. I was offering a (admittedly very strong) counterpoint to OP, which was that I do find a ton of value with claude code. It really has been a game changer to our productivity. Although, based on your response, I did go back to read their original post to see if I mi…

If you have concerns about using the China based API their models are open source and can be ran locally

Re: Claude now has access to a server-side container environment

#342

Post by ctoth »

NamlchakKhandro wrote: post #264
ctoth wrote: post #47

Earlier quoted context omitted.

Curious what a11y issues you see with Claude? I use it a remarkable amount and haven't found any showstoppers. Web interface and Claude Code.

> A blind person like me... you: > what a11y issues you see

Yes. I am also blind. Blind people can use the word "see." Or ... did you have an actual point?

Re: Claude now has access to a server-side container environment

#343

Post by leptons »

dang wrote: post #273
leptons wrote: post #261

Earlier quoted context omitted.

[flagged]

If you keep breaking the site guidelines we will ban you. We've warned you many times, including recently: https://news.ycombinator.com/item?id=44271716 . I don't want to ban you, because you've also posted good things, but we primarily have to moderate based on the bad things people post, and we can't have people attacking others like this. If you'd please review https://news.ycombinator.com/newsguidelines.html and…

People are forgetting they have a brain that can figure things out, don't you think it's worth reminding them that they can figure things out? I weep for the future where people can't do things because ChatGPT is down. My comment was simply trying to remind someone that they have an amazing brain they can use to figure things out. Sorry if that offends you.

Re: Claude now has access to a server-side container environment

#344

Post by michaelmior »

jjice wrote: post #8
michaelmior wrote: post #2

Did anyone else find it bizarre that the user explicitly asked for an Excel document but got a Google Sheet instead?

In the video? It shows that it's an XLSX file, but they used the option to load it into Google Sheets. If you download it, it appears it'd be an XLSX.

Thanks! I missed that part.

Re: Claude now has access to a server-side container environment

#345

Post by dang »

leptons wrote: post #343
dang wrote: post #273

Earlier quoted context omitted.

If you keep breaking the site guidelines we will ban you. We've warned you many times, including recently: https://news.ycombinator.com/item?id=44271716 . I don't want to ban you, because you've also posted good things, but we primarily have to moderate based on the bad things people post, and we can't have people attacking others like this. If you'd please review https://news.ycombinator.com/newsguidelines.html and…

People are forgetting they have a brain that can figure things out, don't you think it's worth reminding them that they can figure things out? I weep for the future where people can't do things because ChatGPT is down. My comment was simply trying to remind someone that they have an amazing brain they can use to figure things out. Sorry if that offends you.

Not offending me - I'm just letting you know that you're breaking the rules and if you keep doing that we will ban you.

Telling someone that by following your instructions they can become "more useful than a tin can" and "might actually learn something", and that they haven't given "figuring it out themselves a try", is for sure over the line into personal attack.

Moreover, if we take all those swipes out of your GP comment, there's literally nothing left! That's definitely not what we want on this site, as should surely be clear from https://news.ycombinator.com/newsguidelines.html.

Re: Claude now has access to a server-side container environment

#346

Post by dang »

rob wrote: post #306
dang wrote: post #233

Earlier quoted context omitted.

I've nicked a sentence from your article to use as the title above. Hope that's clearer!

https://news.ycombinator.com/newsguidelines.html > Otherwise please use the original title, unless it is misleading or linkbait; don't editorialize. The word "container" doesn't even appear in the original post from Anthropic, let alone "server-side container environment."

Yup, that's the rule. I changed the title because the original one was arguably misleading (in much the way that calling a computer a 'file creator and editor' might be), but of course these are not exact arguments and YMMV.

Re: Claude now has access to a server-side container environment

#347

Post by dang »

swyx wrote: post #299
dang wrote: post #233

Earlier quoted context omitted.

I've nicked a sentence from your article to use as the title above. Hope that's clearer!

yeah thats editorializing man, and not the good kind. leave that to simonw's blog.

I was a bit surprised by the pushback on this edit, which seems to me no different than the kind of editing we do day-in-day-out, and have done for a good 15 years.

Editorializing, in my understanding, is introducing spin or opinion, or cherry-picking a detail to highlight only one aspect of a story. It seems to me that this edit doesn't do that because it actually broadens the information in the title and corrects a misleading impression given by the original. The only way I could see this being a bad edit is if it's not actually true that Claude now has access to a server-side container environment. If it's accurate then it surely includes the file-creating-and-editing stuff that was spoken about before, along with a lot more important information—arbitrary computation is rather more than just editing files! No?

More at https://news.ycombinator.com/item?id=45202122.

Re: Claude now has access to a server-side container environment

#348

Post by reissbaker »

sheepscreek wrote: post #217
reissbaker wrote: post #199

Earlier quoted context omitted.

The most private way is to use them on your own machine; a Mac Studio maxed out to 512GB RAM can run GLM-4.5 at FP8 with fairly long context, for example. If you don't have the hardware to run it locally, let me shill my own company for a minute: Synthetic [1] has a $20/month subscription to most of the good open-weight coding LLMs, with higher rate limits than Claude's $20/month sub. And our $60/month sub has higher…

Very impressed with what you're doing. It's not immediately clear how the prompts and the data is used on the site. Your terms mention a 14 day API retention, but it's not clear if that applies to Octo/the CLI agent and any other forms of subscription usage (not through UI). If you can find a way to secure the requests even during the 14 day period, or anonymize them while allowing the developers to do their job, you…

FWIW the 14 day retention is just to cover accidental log statements being deployed — we don't intentionally store API request prompts or completions after processing at all. We'll probably change our stated policy to no-store since in practice that's what we do (and we get this feedback a lot!)

Re: Claude now has access to a server-side container environment

#349

Post by reissbaker »

IgorPartola wrote: post #231
reissbaker wrote: post #199

Earlier quoted context omitted.

The most private way is to use them on your own machine; a Mac Studio maxed out to 512GB RAM can run GLM-4.5 at FP8 with fairly long context, for example. If you don't have the hardware to run it locally, let me shill my own company for a minute: Synthetic [1] has a $20/month subscription to most of the good open-weight coding LLMs, with higher rate limits than Claude's $20/month sub. And our $60/month sub has higher…

Is there a possibility of my work leaning to others? Does your staff have the ability to view prompts and responses? Is tenancy shared with other users, or entities other than your company? This looks really promising since I have also been having all sorts of issues with Claude.

We never train on your prompts or completions, and for the API we don't store longer than 14 days (in fact, we don't ever intentionally store API prompts or completions at all, the 14 day policy was originally just to cover accidental log statements being deployed; we'll probably change it to no-store since it's confusing to say 14 days when we actually don't intentionally store). For the web UI we do have to store, since otherwise we couldn't show you your message history.

In terms of tenancy: we have our own dedicated VMs for our Kubernetes cluster via Azure, although I suspect a VM is not equivalent to an entire hardware node. We use Supabase for our Postgres DB, and Redis for ephemeral data; while we don't share access to that to any other company, we don't create a new DB for every user of our service, so there is user multitenancy there. Similarly, the same GPUs may serve many customers — otherwise we'd need to charge enormous amounts for inference. But, the requests themselves aren't intermingled; i.e. if you make a request, it doesn't affect someone else's.

Re: Claude now has access to a server-side container environment

#350

Post by reissbaker »

AlecSchueler wrote: post #224
reissbaker wrote: post #199

Earlier quoted context omitted.

The most private way is to use them on your own machine; a Mac Studio maxed out to 512GB RAM can run GLM-4.5 at FP8 with fairly long context, for example. If you don't have the hardware to run it locally, let me shill my own company for a minute: Synthetic [1] has a $20/month subscription to most of the good open-weight coding LLMs, with higher rate limits than Claude's $20/month sub. And our $60/month sub has higher…

How do you store/view the data I send you?

For API prompts or completions, we don't store after we return the completion to your prompt (our privacy policy allows us to store for a maximum of 14 days, just to cover accidental log statement deploys). For the web UI we store them in Postgres, since the web UI lets you view your message history and we wouldn't be able to serve that to you without storing it.
Post reply on HN