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

331–340 of 363 posts

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

#331

Post by geeunits »

simonw wrote: post #330
geeunits wrote: post #328

Earlier quoted context omitted.

Don't put the onus (Opus!) on me! Just a dad approach to helping. If there's enough time to writ prose about the problem you could at least rtfm first!

If you know something is covered by the documentation it's useful to provide a link, especially if that documentation is difficult to find. (I couldn't find that documentation when I went looking just now.)

Step 1: https://docs.anthropic.com

Step 2: Type 'Allowed Tools'

Step 3: Click: https://docs.anthropic.com/en/docs/claude-code/sdk/sdk-headl...

Step 4: Read

Step 5: Example --allowedTools "Read,Grep,WebSearch"

Step 6: Profit?

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

#332

Post by idonotknowwhy »

spicybright wrote: post #54
mh- wrote: post #15

Earlier quoted context omitted.

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…

Glad I'm not crazy. I actually noticed both 4 models are just garbage. I started running my prompts through those, and Sonnet 3.7 comparing the results. Sonnet 3.7 is way better at everything.

You're not crazy, and this isn't new for Anthropic. Something is off with Opus4.1, I actually saw it make 2 "typos" last week (I've never seen a model like this make a dumb "typo" before). And it's missing details that it understood last month (can easily test this if you have some chats in OpenWebUI or LibreChat, just go in and hit regenerate).

Sonnet 3.5 did this last year a few times, it'd have days where it wasn't working properly, and sure enough, I'd jump online and see "Claude's been lobotomized again".

They also experiment with injecting hidden system prompts from time to time. Eg. if you ask for a story about some IP, it'll interrupt your prompt and remind the model not to infringe copyright. (We could see this via API with prompt engineering, adding a "!repeat" "debug prompt" that revealed it, though they seem to have patched that now.

> I started running my prompts through those, and Sonnet 3.7 comparing the results. Sonnet 3.7 is way better at everything.

Same here. And on API, the old Opus 3 is also unaffected (though that model is too old for coding).

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

#333

Post by brumar »

simonw wrote: post #155

I just published an extensive review of the new feature, which is actually Claude Code Interpreter (the official name, bafflingly, is Upgraded file creation and analysis - that's what you turn on in the features page at least). I reverse-engineered it a bit, figured out its container specs, used it to render a PDF join diagram for a SQLite database and then re-ran a much more complex "recreate this chart from this sc…

These days, I spend time training people using this kind of tools. I am glad it's called as such. It's much comfortable to explain to a tech person that it's "badly named" and that it should have been named "Code Interpreter" instead than explaining to a non tech that the "Code Interpreter" feature is a new cool way to generate documents. Most people are not that comfortable with technology, so avoiding big words is a nice to have.

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

#334

Post by mkw2000 »

allisdust wrote: post #296
allisdust wrote: post #286

Earlier quoted context omitted.

Yes it is. But totally worth it. Just got it and its quite good and quite fast. Clearly they are subsidizing even at $6. It feels like using sonnet speed wise but with opus quality (i mean pre August Opus/sonnet -> no clue what Anthropic did after that. It's just crap now).

This model is funny to say the least: > /cost ⎿ Total cost: $50.42 Total duration (API): 1h 3m 2.3s Total duration (wall): 3h 36m 56.4s Total code changes: 1205 lines added, 350 lines removed Usage by model: claude-3-5-haiku: 89.5k input, 2.1k output, 15.7k cache read, 0 cache write claude-sonnet: 15.7m input, 84.8k output, 6.5m cache read, 0 cache write > what model are you ? ● I'm Claude Sonnet (the model shown in…

Funniest moment for me so far was when i emailed z-ai to ask if there is a way i can upgrade my plan to the higher tier and they were just like "sorry, nope"

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

#335

Post by plaguuuuuu »

mdaniel wrote: post #198
simonw wrote: post #155

I just published an extensive review of the new feature, which is actually Claude Code Interpreter (the official name, bafflingly, is Upgraded file creation and analysis - that's what you turn on in the features page at least). I reverse-engineered it a bit, figured out its container specs, used it to render a PDF join diagram for a SQLite database and then re-ran a much more complex "recreate this chart from this sc…

> Version Control > github.com pour one out for the GitLab hosted projects, or its less popular friends hosted on bitbucket, codeberg, forgejo, sourceforge, sourcehut, et al. So dumb.

If they made Git decentralised, so that you could mirror stuff on github, it might solve that issue!

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

#336

Post by simonw »

geeunits wrote: post #331
simonw wrote: post #330

Earlier quoted context omitted.

If you know something is covered by the documentation it's useful to provide a link, especially if that documentation is difficult to find. (I couldn't find that documentation when I went looking just now.)

Step 1: https://docs.anthropic.com Step 2: Type 'Allowed Tools' Step 3: Click: https://docs.anthropic.com/en/docs/claude-code/sdk/sdk-headl... Step 4: Read Step 5: Example --allowedTools "Read,Grep,WebSearch" Step 6: Profit?

The original question was about this:

> allow zoned access enforcement within files. I want to be able to say "this section of the file is for testing", delineated by comments, and forbid Claude from editing it without permission.

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

#337

Post by sunaookami »

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…

It edits it for me but it tries to edit it "in place" where it messes up the version history and it looks very broken and often times is broken afterwards. Don't know why they broke their best feature while ChatGPT Canvas just works.

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

#338

Post by atonse »

ranguna wrote: post #311
atonse wrote: post #274

Earlier quoted context omitted.

I pay $100 a month and wouldn’t hesitate for a millisecond if I needed to pay the $200/mo plan if I hit rate limits. It’s hard to overstate how much of a productivity shift Claude code has been for shipping major features in our app. And ours is an elixir app. It’s even better with React/NextJS. I literally won’t be hitting any “I need to hire another programmer to handle this workload” limits any time soon.

That's not what the op asked. They didn't ask whether claude is useful in general, they asked whether it was good compared to other LLMs. On of the tricks to a healthy discussions is to actually read/listen to what the other side is trying to say. Without that, you're just talking to yourself.

If my tone came off as confrontational, that was not my intent. But I do intend to say this: It seems to me that _you_ are ascribing malice to my comment. I was offering a (admittedly very strong) counterpoint to OP, which was that I do find a ton of value with claude code. It really has been a game changer to our productivity.

Although, based on your response, I did go back to read their original post to see if I missed some nuance, and I did.

They were talking about using the alternate model WITH Claude Code. I didn't know that was an option, and would definitely be willing to try things out (as we all are experimenting a lot these days).

At the end of the day, it's less about Claude Code, but that form of coding. It's not perfect by any stretch, but it has changed my ability to ship features in HUGE ways.

Update: This is not a comment on the technical strength of z.ai, but I would have concerns about it being based in China. This isn't insurmountable, like with companies like Zoom that are Chinese owned but guarantee US-based servers/data/staff, etc. But I suspect that will hold many back. Again, everyone's a grownup here, and I'm sure z.ai already has a plan to address that "weakness" in their value.

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

#339

Post by blyat »

zarzavat wrote: post #291
brookst wrote: post #260

Earlier quoted context omitted.

Same plan, same experience. Trying to get it to develop and execute tests and it frequently modifies the test to succeed even if the libraries it calls fail, and then explains that it’s doing so because the test itself works but the underlying app has errors. Yes, I know. That’s what the test was for.

Anthropic, if you're listening, please allow zoned access enforcement within files. I want to be able to say "this section of the file is for testing", delineated by comments, and forbid Claude from editing it without permission. My fear when using Claude is that it will change a test and I won't notice. Splitting tests into different files works but it's often not feasible, e.g. if I want to write unit tests for a s…

I've had some middling success with this by utilizing CLAUDE.md and language features. Two approaches in C#: 1) use partial classes and create a 'rule' in CLAUDE.md to never touch named files, e.g. User.cs (edits allowed) User.Protected.cs (not allowed by convention) and 2) a no-AI-allowed attribute, e.g. [DontModifyThisClassOrAttributeOrMethodOrWhatever] and instructions to never modify said target. Can be much more granular and Claude Code seems to respect it.

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

#340

Post by currymj »

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 way it edits powerpoints is by launching a command line environment, and then editing the OOXML directly using command line tools. this takes several minutes to do even simple changes.

to me it seems miraculous that it even "sort of" works, but also it's not a reliable product yet. OOXML is very complex and the formatting can get mangled.

On the other hand, if you use LaTeX/Beamer slides, LLMs can reliably make a lot of formatting tweaks etc. and it is an actual time saver. But only weird academics use Beamer.

I agree with Simon Willison that this feature is really about writing code in a container, using that capability to edit PPT presentations as if they were markup is an odd thing to make the primary selling point.

Post reply on HN