Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude 3.7 Sonnet and Claude Code

anthropic.com

Post reply on HN
Print view View original

221–230 of 1001 posts

Re: Claude 3.7 Sonnet and Claude Code

#221

Post by bcherny »

Flux159 wrote: post #166
bcherny wrote: post #91

Hi everyone! Boris from the Claude Code team here. @eschluntz, @catherinewu, @wolffiex, @bdr and I will be around for the next hour or so and we'll do our best to answer your questions about the product.

Is there a way to always accept certain commands across sessions? Specifically for things like reading or updating files I don't want to have to approve that each time I open a new repl. Also, is there a way to switch models between 3.5-sonnet and 3.5-sonnet-thinking? Got the initial impression that the thinking model is using an excessive amount of tokens on first use.

When you are prompted to accept a bash command, we should be giving you the option to not ask again. If you're not seeing that for a specific bash command, would you mind running /bug or filing an issue on Github? https://github.com/anthropics/claude-code/issues

Thinking and not thinking is actually the same model! The model thinks automatically when you ask it to. If you don't explicitly ask it to think, it won't use thinking.

Re: Claude 3.7 Sonnet and Claude Code

#222

Post by sealthedeal »

eschluntz wrote: post #160
pookieinc wrote: post #108

Earlier quoted context omitted.

The biggest complaint I (and several others) have is that we continuously hit the limit via the UI after even just a few intensive queries. Of course, we can use the console API, but then we lose ability to have things like Projects, etc. Do you foresee these limitations increasing anytime soon? Quick Edit: Just wanted to also say thank you for all your hard work, Claude has been phenomenal.

We are definitely aware of this (and working on it for the web UI), and that's why Claude Code goes directly through the API!

I haven't been able to find ClaudeCLI for pubic access yet. Would love to use.

Re: Claude 3.7 Sonnet and Claude Code

#224

Post by nprateem »

bcherny wrote: post #91

Hi everyone! Boris from the Claude Code team here. @eschluntz, @catherinewu, @wolffiex, @bdr and I will be around for the next hour or so and we'll do our best to answer your questions about the product.

Does this actually have an 8k (or more) output context via the API?

3.5 did with a beta header but while 3.6 claimed to, it always cut its responses after 4k.

IIRC someone reported it on GH but had no reply.

Re: Claude 3.7 Sonnet and Claude Code

#225

Post by waltercool »

azinman2 wrote: post #61
waltercool wrote: post #33

Just like OpenAI or Grok, there is no transparency and no way for self-hosting purposes. Your input and confidential information can be collected for training purposes. I just don't trust those companies when you use their servers. This is not a good approach to LLM democratization.

I wouldn’t assume there’s no way to self host — it just costs a lot more than open weights. Anthropic claims they don’t train on their inputs. I haven’t seen any reason to disbelieve them.

But there is no way to know if their claims are true either. Your inputs are processed into their servers, then you get a response. Whatever happens in the middle, only Anthropic knows. We don't even know of governments are actually pushing AI companies to enforce censorship or spying people, like we seen recently at UK government getting into Apple E2E encryption.

This criticism is valid for the business who wants to use AI to improve coding, code analysis or code review, documentation, emails, etc, but also for that individual who don't want to rely on 3rd party companies for AI usage.

Re: Claude 3.7 Sonnet and Claude Code

#226

Post by catherinewu »

curl-up wrote: post #116
bcherny wrote: post #91

Hi everyone! Boris from the Claude Code team here. @eschluntz, @catherinewu, @wolffiex, @bdr and I will be around for the next hour or so and we'll do our best to answer your questions about the product.

In the console, TPM limit for 3.7 is not shown (I'm tier 4). Does it mean there is no limit, or is it just pending and is "variable" until you set it to some value?

We set the Claude Code rate limits to be usable as a daily driver. We expect hitting rate limits for synchronous usage to be uncommon. Since this is a research preview, we recommend you start small as you try the product though.

Re: Claude 3.7 Sonnet and Claude Code

#227

Post by airstrike »

punkpeye wrote: post #212
pookieinc wrote: post #108

Earlier quoted context omitted.

The biggest complaint I (and several others) have is that we continuously hit the limit via the UI after even just a few intensive queries. Of course, we can use the console API, but then we lose ability to have things like Projects, etc. Do you foresee these limitations increasing anytime soon? Quick Edit: Just wanted to also say thank you for all your hard work, Claude has been phenomenal.

If you are open to alternatives, try https://glama.ai/gateway We currently serve ~10bn tokens per day (across all models). OpenAI compatible API. No rate limits. Built in logging and tracing. I work with LLMs every day, so I am always on top of adding models. 3.7 is also already available. https://glama.ai/models/claude-3-7-sonnet-20250219 The gateway is integrated directly into our chat ( https://glama.ai/chat ). So…

The issue isn't API limits, but web UI limits. We can always get around the web interface's limits by using the claude API directly but then you need to have some other interface...

Re: Claude 3.7 Sonnet and Claude Code

#228

Post by wolffiex »

batterylake wrote: post #181

Hi Claude Code team, excited for the launch! How well does Claude Code do on tasks which rely heavily on visual input such as frontend web dev or creating data visualizations?

As a CLI, this tool is most efficient when it can see text outputs from the commands that it runs. But you can help it with visual tasks by putting a screenshot file in your project directory and telling claude to read it, or by copying an image to your clipboard and pasting it with CTRL+V

Re: Claude 3.7 Sonnet and Claude Code

#229

Post by fsndz »

keithwhor wrote: post #161
fsndz wrote: post #129

Earlier quoted context omitted.

Anthropic is back and cementing its place as the creator of the best coding models—bravo! With Claude Code, the goal is clearly to take a slice of Cursor and its competitors' market share. I expected this to happen eventually. The app layer has barely any moat, so any successful app with the potential to generate significant revenue will eventually be absorbed by foundation model companies in their quest for growth a…

I think an argument could be reasonably made that the app layer is the only moat. It’s more likely Anthropic eventually has to acquire Cursor to cement a position here than they out-compete it. Where, why, what brand and what product customers swipe their credit cards for matters — a lot.

if Claude Code offers a better experience, users will rapidly move from cursor to Claude Code.

Claude is for Code: https://medium.com/thoughts-on-machine-learning/claude-is-fo...

Re: Claude 3.7 Sonnet and Claude Code

#230

Post by antirez »

bcherny wrote: post #91

Hi everyone! Boris from the Claude Code team here. @eschluntz, @catherinewu, @wolffiex, @bdr and I will be around for the next hour or so and we'll do our best to answer your questions about the product.

One of the silver bullets of Claude, in the context of coding, is that it does NOT use RAG when you use it via the web interface. Sure, you burn your tokens but the model sees everything and this let it reply in a much better way. Is Claude Code doing the same and just doing document-level RAG, so that if a document is relevant and if it fits, all the document will be put inside the context window? I really hope so! Also, this means that splitting large code bases into manageable file sizes will make more and more sense. Another Q: is the context size of Sonnet 3.7 the same of 3.5? Btw Thanks you so much for Claude Sonnet, in the latest months it changed the way I work and I'm able to do a lot more, now.
Post reply on HN