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

181–190 of 363 posts

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

#181

Post by bobbylarrybobby »

pmx wrote: post #3

They need to focus on fixing reliability first. Their systems constantly go down and it appears they are having to quantise the models to keep up with demand, reducing intelligence significantly. New features like this feel pointless when the underlying model is becoming unusable.

Their iOS app could use some serious love. Not only does it have no offline capabilities (you can't even read your previous chats), if you're using the app and go offline, it puts up a big “connection lost; retry” alert and won't let you interact with the app until you get internet again. That means if you're mid prompt, you're blocked from editing further, and if you're reading a response, you have to wait until you get cell service again to continue reading.

It's one thing to not cache things for offline use, but it's quite another to intentionally unload items currently in use just because the internet connection dropped!

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

#183

Post by jimbo808 »

reissbaker wrote: post #172
data-ottawa wrote: post #63

Earlier quoted context omitted.

I don’t think you’re crazy, something is off in their models. As an example I’ve been using an MCP tool to provide table schemas to Claude for months. There was a point where it stopped recognizing the tool unless mentioned in early August. Maybe that’s related to their degraded quality issue. This morning after pulling the correct schema info Sonnet started hallucinating columns (from Shopify’s API docs) and added t…

FWIW I strongly recommend using some of the recent, good Chinese OSS models. I love GLM-4.5, and Kimi K2 0905 is quite good as well.

I'd like to give these a try - what's your way of using them? I mostly use Claude because of Claude Code. Not sure what agentic coding tools people are using these days with OSS models. I'm not a big fan of manually uploading files into a web UI.

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

#184

Post by bobbylarrybobby »

visarga wrote: post #109
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.

Claude has no TTS while most LLMs have it. It makes the text more accessible.

The iOS just gained tts, although for some reason it doesn't use the voice mode voice and sounds really really bad. But it's technically there.

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

#185

Post by jononor »

brandon272 wrote: post #88
OtomotO wrote: post #71

Earlier quoted context omitted.

This, so much this... I signed up for Claude over a week ago and I totally regret it! Previously I was using it and some ChatGPT here and there (also had a subscription in the past) and I felt like Claude added some more value. But it's getting so unstable. It generates code, I see it doing that, and then it throws the code away and gives me the previous version of something 1:1 as a new version. And then I have to w…

> But it's getting so unstable. It generates code, I see it doing that, and then it throws the code away and gives me the previous version of something 1:1 as a new version. I've had the same experience. Totally unreliable.

This happens to me a lot. Almost once per session now, and not even when things are complicated. The model also thinks it has done the changes. So it seems a UI/state bug, not on the model side.

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

#187

Post by bobbylarrybobby »

lordnacho wrote: post #56

This will either result in a lot of people being able to sleep more, or an absolute avalanche of crap is about to be released upon society. A lot of the people I graduated with spent their 20s making powerpoint and excel. There would be people with a master's in engineering getting phone calls at 1am, with an instruction to change the fonts on slide 75, or to slightly modify some calculation. Most of the real decisio…

When the word processor was first invented, people didn't end up printing less because of how easy it was to edit and view documents live — they printed more because of how little friction there was (compared to a typewriter) between making a change and pressing print.

I think we're going to see the same thing with document creation. Could LLMs help make a small number of high quality documents? Yes, with some coaching and planning from the user. But instead people will use them to quickly create a crappy document, get feedback that it's crappy, and then immediately create an only slightly less crappy doc.

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

#188

Post by jononor »

amilios wrote: post #123

Anyone else having serious reliability issues with artifact editing? I find that the artifacts quite often get "stuck", where the LLM is trying to edit the artifact but the state of the artifact does not change. Seems like the LLM is somehow failing in editing the artifact silently, while thinking that it is actually doing the edits. The way to resolve this is to ask Claude to make a new artifact, which then has all…

Yes every 10 edits or so. Super annoying. It is limiting how often I bother using the tool

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

#189

Post by typpilol »

syntaxing wrote: post #142
pmx wrote: post #3

They need to focus on fixing reliability first. Their systems constantly go down and it appears they are having to quantise the models to keep up with demand, reducing intelligence significantly. New features like this feel pointless when the underlying model is becoming unusable.

I wonder if their API model is different from the subscription model. People called me crazy saying how GitHub copilot is better than Clause code but since I started using Claude code these past 3 weeks, times and times again, copilot + Claude sonnet 4 is better

Agreed.. copilot is way better

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

#190

Post by leptons »

pmx wrote: post #3

They need to focus on fixing reliability first. Their systems constantly go down and it appears they are having to quantise the models to keep up with demand, reducing intelligence significantly. New features like this feel pointless when the underlying model is becoming unusable.

How much are you willing to pay for it? Maybe they just need a few billion more dollars to shovel into the furnace to keep the "AI" going faster.
Post reply on HN