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

11–20 of 363 posts

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

#11

Post by pqdbr »

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.)

Same here. Even with Opus in Claude Code I'm getting terrible results, sometimes feeling we went back to the GPT 3.5 eon. And it seems they are implementing heavily token-saving measures: the model does not read context anymore unless you force it to, making up method calls as it goes.

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

#12

Post by swalsh »

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.

The people shipping these features are not the same people who are fixing reliability probably.

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

#13

Post by Rickasaurus »

catlifeonmars wrote: post #5
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.

What does it mean to quantise a model?

It means to change representation to less bits per number floating point, lower resolution numbers

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

#14

Post by stirfish »

catlifeonmars wrote: post #5
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.

What does it mean to quantise a model?

Basically you trade accuracy for space, so you use fewer resources

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

#15

Post by mh- »

pqdbr wrote: post #11
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.)

Same here. Even with Opus in Claude Code I'm getting terrible results, sometimes feeling we went back to the GPT 3.5 eon. And it seems they are implementing heavily token-saving measures: the model does not read context anymore unless you force it to, making up method calls as it goes.

The simplest thing I frequently ask of regular Claude (not Code) in the desktop app:

"Use your web search tool to find me the go-to component for doing xyz in $language $framework. Always link the GitHub repo in your response."

Previously Sonnet 4 would return a good answer to this at least 80% of the time.

Now even Opus 4.1 with extended thinking frequently ignores my ask for it to use the search tool, which allows it to hallucinate a component in a library. Or maybe an entire repo.

It's gone backwards severely.

(If someone from Anthropic sees this, feel free to reach out for chat IDs/share links. I have dozens.)

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

#16

Post by SubiculumCode »

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.

Normally, I'd say yeah right, but I've been kind of feeling this too...and the thing is, we can't really know what they are running. It would be nice to have a private eval metric to monitor these things over time.

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

#17

Post by BrawnyBadger53 »

catlifeonmars wrote: post #5
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.

What does it mean to quantise a model?

Reducing the number of bits per float, it's like compression for models

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

#18

Post by esafak »

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.

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

#19

Post by ACCount37 »

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.

Anthropic claims that they don't degrade models under load, and the performance issues were a result of a system error:

https://status.anthropic.com/incidents/72f99lh1cj2c

That being said, they still have capacity issues on any day of the week that ends in Y. No clue how long would that take to resolve.

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

#20

Post by SubiculumCode »

I noticed the other day that chatgpt started preferring to provide me with a download link for code rather than putting it up in canvas. It also started offering me diffs, but as I just write fairly basic data munging scripts for neuroimaging analyses, I don't like to dive too deep into the coding tool boxes/chains...copy paste is easy...although, I would like versioning without making copies of my script for backup
Post reply on HN