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

91–100 of 363 posts

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

#91

Post by rapind »

furyofantares wrote: post #23
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.

Some of this has gotta be people asking more of it than they did before, and some has gotta be people who happened to use it for things it's good at to begin with and are now asking it things it's bad at (not necessarily harder things, just harder for the model). However there have been some bugs causing performance degradation acknowledged by Anthropic as well (and fixed) and so I would guess there's a good amount o…

What makes it particularly tricky to evaluate is that there could still be other bugs given how long these went without even acknowledgement until now, and they did state they are still looking into potential Opus issues.

I'll probably come back and try a Claude Code subscription again, but I'm good for the time being with the alternative I found. I also kind of suspect the subscription model isn't going to work for me long term and instead the pay per use approach (possibly with reserved time like we have for cloud compute) where I can swap models with low friction is far more appealing.

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

#92

Post by darepublic »

Wasn't this already doable? Via instructing the llm to output as PDF xml or PowerPoint markup etc and writing (with AI assistance) the glue layer. It's not nothing but also not that difficult. I don't see how Claude's version of this can be much better

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

#93

Post by mattnewton »

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…

The global economy has been down the rabbit hole and through the looking glass into the land of the red queen as far as I’ve known.

“Now here you see, it takes all the running you can do, to keep in the same place” as she says.

I fully believe any slack this creates will get gobbled up in competition in a few years.

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

#94

Post by stpedgwdgfhgdd »

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 did not notice a degradation in quality last weeks. Not saying it is perfect, but the quality is similar (using Sonet) for the last month.

Using only 2 MCP servers and not extending claude.md.

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

#95

Post by mattbettinson »

eatsyourtacos wrote: post #51
probably_wrong wrote: post #30

Earlier quoted context omitted.

Have you considered perhaps that you are, indeed, out of your mind? Or more precisely, that you could be rationalizing what is essentially a random process? Based on the discussions here it seems that every model is either about to be great or was great in the past but now is not. Sucks for those of us who are stuck in the now , though.

>Or more precisely, that you could be rationalizing what is essentially a random process? You mean like our human brains and our entire bodies? We are the result of random processes. >Sucks for those of us who are stuck in the now, though I don't know what you are doing- but GPT5 is incredible. I literally spent 3 hours last night going back and forth on a project where I loaded some files for a somewhat complicated…

But would you have hired a junior dev for that work if AI hadn't 'replaced' it?

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

#96

Post by rapind »

esafak wrote: post #18
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 have not noticed a degradation in Claude, but I feel that with Gemini 2.5 Pro.

Apparently the "bugs" only affected some users... which in itself is kind of worrisome... I suspect the changes they made to limit abusers might have been misclassifying some "good" users. Like shadow throttling. This is just a suspicion based on possibly coincidental timing though.

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

#97

Post by grim_io »

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…

I guess it will decrease the need for custom software. If this is reliable, excel will be "enough" for longer.

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

#98

Post by hu3 »

mikewarot wrote: post #81

Not Claude specific, but related to the agent model of things... I've been paying $10/month for GitHub Copilot, which I use via Microsoft's Visual Studio Code, and about a month ago, they added ChatGPT5 (preview), which uses the agent model of interaction. It's a qualitative jump that I'm still learning to appreciate in full. It seems like the worst possible thing, in terms of security, to let an LLM play with your s…

Yeah in agent mode it compiles code and runs tests, if anything breaks it attempts to fix. Kinda wild to see at first.

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

#99

Post by yazanobeidi »

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.

Have you run into the bug where claude acts as if it updated the artifact, but it didn’t? You can see the changes in real time, but then suddenly it’s all deleted character by character as if the backspace was held down, you’re left with the previous version, but claude carries on as if everything is fine. If you point it out, it will acknowledge this, try again, and… same thing. The only reliable fix I’ve seen is to ask it to generate a new artifact with that content and the updates. Talk about wasting tokens, and no refunds, no support, you’re on your own entirely. It’s unclear how they can seriously talk about releasing this feature when there are fundamental issues with their existing artifact creation and editing abilities.
Post reply on HN