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

121–130 of 363 posts

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

#121

Post by j45 »

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.

I’m running into this as well.

Might be Claude optimizing for general use cases compared to code and that affecting the code side?

Feels strange, because Claude api isn’t the same as the web tool so I didn’t expect Claude code to be the same.

It might be a case of having to learn to read Claude best practice docs and keep up with them. Normally I’d have Claude read them itself and update an approach to use. Not sure that works as well anymore.

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

#122

Post by otabdeveloper4 »

sfn42 wrote: post #74
imiric wrote: post #25

Earlier quoted context omitted.

Wait—surely they're dogfooding Claude for infrastructure tasks, making existing engineers 10x as productive, requiring less human engineers overall?

Why are these AI companies still hiring? If their "AI"s are so awesome and make devs 10x shouldn't they be firing?

AI is the biggest productivity boost in human history since the invention of writing. It only makes sense that they need 100x and 10000x engineers!

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

#123

Post by amilios »

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 the changes Claude thought it was making. But you have to do this relatively often.

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

#124

Post by j45 »

fuomag9 wrote: post #101
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 felt like the model degraded lately as well, I've been using Claude everyday for months now

I’m considering trying the api directly for a bit with Claude code to compare but need a test quite first to compare all 3.

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

#125

Post by allisdust »

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.)

Yup. Opus 4.1 has been feeling like absolute dog shit and it made me give up in frustration several times. They really did downgrade their models. Max plan is a joke now. I'm barely using Pro level tokens since its a net negative on my productivity. Enshittification is now truly in place.

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

#126

Post by mh- »

yazanobeidi wrote: post #99
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…

Yes, just had it happen a couple nights ago with a simple one pager I asked it to generate from some text in a project. It couldn't edit the existing artifact (I could see it being confused as to why the update wasn't taking in the CoT), so it made a new version for every incremental edit. Which of course means there were other changes too, since it was generating from scratch each time.

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

#127

Post by trunnell »

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.)

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

They recently resolved two bugs affecting model quality, one of which was in production Aug 5-Sep 4. They also wrote:

  Importantly, we never intentionally degrade model quality as a result of demand or other factors, and the issues mentioned above stem from unrelated bugs.
Sibling comments are claiming the opposite, attributing malice where the company itself says it was a screw up. Perhaps we should take Anthropic at its word, and also recognize that model performance will follow a probability distribution even for similar tasks, even without bugs making thing worse.

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

#128

Post by trunnell »

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.

They need to focus on fixing reliability first.

Maybe. What would you rather have?

A) rock solid Sonnet 4 with Sonnet 5, say, next April

B) buggy Sonnet 4 with Sonnet 5, say, next January

Seems like different customers would have a range of preferences.

This must be one of the questions facing the team at Anthropic: what proportion of effort should go towards quality vs. velocity?

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

#129

Post by mh- »

trunnell wrote: post #127
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.)

https://status.anthropic.com/incidents/72f99lh1cj2c They recently resolved two bugs affecting model quality, one of which was in production Aug 5-Sep 4. They also wrote: Importantly, we never intentionally degrade model quality as a result of demand or other factors, and the issues mentioned above stem from unrelated bugs. Sibling comments are claiming the opposite, attributing malice where the company itself says it…

The problem is twofold:

- They're reporting that only impacted Haiku 3.5 and Sonnet 4. I used neither model during the time period I'm concerned with.

- It took them a month to publicly acknowledge that issue, so now we lack confidence there isn't another underlying issue going undetected (or undisclosed, less charitably) that affects Opus.

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

#130

Post by ffsm8 »

amelius wrote: post #113
hu3 wrote: post #98

Earlier quoted context omitted.

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).

That's what devcontainers are for. You create the config and the editor runs effectively inside of the docker container. Works surprisingly good. Vscode for example even Auto proxies opened ports inside of the container to the host etc.

Will also make using Linux tooling a lot easier on non- Linux hosts like Windows/MacOS

Post reply on HN