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

111–120 of 363 posts

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

#111

Post by FitchApps »

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.

Time to revisit the infamous "3 to 6 months, AI will be writing 90% of the code" statement. I wonder how the team is doing and what % of code is being written by AI at Athropic.

https://www.businessinsider.com/anthropic-ceo-ai-90-percent-...

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

#112

Post by otabdeveloper4 »

mh- wrote: post #4
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.

This can't be understated. I started using it heavily earlier this summer and it felt like magic. Someone signing up now based on how I described my personal experiences with it then would think I was out of my mind . For technical tasks it has been a net negative for me for the last several weeks. (Speaking of both Claude Code and the desktop app, both Sonnet and Opus >=4, on the Max plan.)

Congrats, you grew up. It's not Claude's fault.

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

#113

Post by amelius »

hu3 wrote: post #98
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.

I'd probably install a snapshotting filesystem before I let it change stuff on my system (such as installing packages and such).

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

#114

Post by j45 »

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 hit a limit this morning so fast and the quantization makes me think of different models.

Sonnet was nearly unusable without a perfect prompt and it took a separate therapy session with another sonnet chat to deconstruct how it was no lager working.

There appear to be hard overrides being introduced that overlook basic things like using your personal preferences.

Vague or general descriptions get weighed less important vs the strong and clear.

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

#115

Post by j45 »

probably_wrong wrote: post #30
mh- wrote: post #4

Earlier quoted context omitted.

This can't be understated. I started using it heavily earlier this summer and it felt like magic. Someone signing up now based on how I described my personal experiences with it then would think I was out of my mind . For technical tasks it has been a net negative for me for the last several weeks. (Speaking of both Claude Code and the desktop app, both Sonnet and Opus >=4, on the Max plan.)

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.

Just because one can’t concieve something being possible doesn’t mean it’s not possible.

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

#116

Post by otabdeveloper4 »

pc86 wrote: post #28
mh- wrote: post #4

Earlier quoted context omitted.

This can't be understated. I started using it heavily earlier this summer and it felt like magic. Someone signing up now based on how I described my personal experiences with it then would think I was out of my mind . For technical tasks it has been a net negative for me for the last several weeks. (Speaking of both Claude Code and the desktop app, both Sonnet and Opus >=4, on the Max plan.)

I hesitate to use phrases like "bait and switch" but it seems like every model gets released and is borderline awe-inspiring, then as adoption increases, and load increases, it's like it gets hit in the head with a hammer and is basically useless for anything beyond a multi-step google search.

No, that's just the normal slope of the hype curve as you start figuring out how the man behind the curtain operates.

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

#117

Post by j45 »

hkt wrote: post #45
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.

It seems plausible enough that they're trying to squeeze as much out of their hardware as possible and getting the balance wrong. As prices for hardware capable of running local LLMs drop and local models improve, this will become less prevalent and the option of running your own will become more widespread, probably killing this kind of service outside of enterprise. Even if it doesn't kill that service, it'll be _c…

Thanks. Mind sharing which kinds of Claude tasks you are able to run on qwen3:4b?

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

#118

Post by j45 »

mattbettinson wrote: post #95
eatsyourtacos wrote: post #51

Earlier quoted context omitted.

>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?

Not a valid response in all cases.

It might not be a junior dev tool. Senior devs are using AI quite differently to magnify themselves not help them manage juniors with developing ceilings.

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

#119

Post by j45 »

pc86 wrote: post #28
mh- wrote: post #4

Earlier quoted context omitted.

This can't be understated. I started using it heavily earlier this summer and it felt like magic. Someone signing up now based on how I described my personal experiences with it then would think I was out of my mind . For technical tasks it has been a net negative for me for the last several weeks. (Speaking of both Claude Code and the desktop app, both Sonnet and Opus >=4, on the Max plan.)

I hesitate to use phrases like "bait and switch" but it seems like every model gets released and is borderline awe-inspiring, then as adoption increases, and load increases, it's like it gets hit in the head with a hammer and is basically useless for anything beyond a multi-step google search.

It’s important to jump on new models super early while the rails get out in.

Anyone remember GPT4 the day it launched? :)

Post reply on HN