Most active commenters

    ←back to thread

    Claude 3.7 Sonnet and Claude Code

    (www.anthropic.com)
    2127 points bakugo | 13 comments | 24 Feb 25 18:28 UTC | HN request time: 0s | source | bottom
    Show context
    bcherny ◴[24 Feb 25 19:04 UTC] No.43163488[source]▶
    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.
    replies(82): >>43163527 #>>43163532 #>>43163549 #>>43163554 #>>43163555 #>>43163576 #>>43163585 #>>43163588 #>>43163589 #>>43163592 #>>43163593 #>>43163632 #>>43163642 #>>43163664 #>>43163677 #>>43163733 #>>43163758 #>>43163789 #>>43163803 #>>43163813 #>>43163821 #>>43163893 #>>43163909 #>>43163915 #>>43163921 #>>43163957 #>>43163958 #>>43163992 #>>43164069 #>>43164089 #>>43164102 #>>43164103 #>>43164104 #>>43164111 #>>43164127 #>>43164158 #>>43164329 #>>43164353 #>>43164424 #>>43164482 #>>43164514 #>>43164585 #>>43164616 #>>43164768 #>>43164797 #>>43164819 #>>43164899 #>>43165002 #>>43165057 #>>43165065 #>>43165088 #>>43165091 #>>43165187 #>>43165308 #>>43165355 #>>43165409 #>>43165468 #>>43165499 #>>43165516 #>>43165570 #>>43165578 #>>43165592 #>>43165836 #>>43165884 #>>43165965 #>>43165976 #>>43165995 #>>43166183 #>>43166711 #>>43166748 #>>43167130 #>>43167804 #>>43168626 #>>43168836 #>>43169047 #>>43169107 #>>43169119 #>>43169294 #>>43169310 #>>43173097 #>>43174353 #>>43192161 #
    pookieinc ◴[24 Feb 25 19:09 UTC] No.43163554[source]▶
    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.

    replies(4): >>43163771 #>>43163889 #>>43164021 #>>43167940 #
    1. eschluntz ◴[24 Feb 25 19:25 UTC] No.43163771[source]▶
    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!
    replies(3): >>43163984 #>>43164057 #>>43167719 #
    2. smallerfish ◴[24 Feb 25 19:42 UTC] No.43163984[source]▶
    I'm sure many of us would gladly pay more to get 3-5x the limit.

    And I'm also sure that you're working on it, but some kind of auto-summarization of facts to reduce the context in order to avoid penalizing long threads would be sweet.

    I don't know if your internal users are dogfooding the product that has user limits, so you may not have had this feedback - it makes me irritable/stressed to know that I'm running up close to the limit without having gotten to the bottom of a bug. I don't think stress response in your users is a desirable thing :).

    replies(2): >>43165060 #>>43165318 #
    3. sealthedeal ◴[24 Feb 25 19:48 UTC] No.43164057[source]▶
    I haven't been able to find ClaudeCLI for pubic access yet. Would love to use.
    replies(2): >>43164217 #>>43165657 #
    4. eschluntz ◴[24 Feb 25 20:01 UTC] No.43164217[source]▶
    >>> npm install -g @anthropic-ai/claude-code

    >>> claude

    5. justinbaker84 ◴[24 Feb 25 21:45 UTC] No.43165318[source]▶
    This is the main point I always want to communicate to the teams building foundation models.

    A lot of people just want the ability to pay more in order to get more.

    I would gladly pay 10x more to get relatively modest increases in performance. That is how important the intelligence is.

    replies(1): >>43166135 #
    6. kkarpkkarp ◴[24 Feb 25 22:25 UTC] No.43165657[source]▶
    see https://docs.anthropic.com/en/docs/agents-and-tools/claude-c...
    7. willsmith72 ◴[24 Feb 25 23:21 UTC] No.43166135{3}[source]▶
    As a growth company, they likely would prefer a larger amount of users even with occasional rate limits, vs smaller pool of power users.

    As long as capacity is an issue, you can't have both

    replies(1): >>43166920 #
    8. cruffle_duffle ◴[25 Feb 25 01:17 UTC] No.43166920{4}[source]▶
    If people are paying for use, then why can’t you have both?
    replies(1): >>43167140 #
    9. saulpw ◴[25 Feb 25 01:50 UTC] No.43167140{5}[source]▶
    It takes time to grow capacity to meet growing revenue/usage. As parent is saying, if you are in a growth market at time T with capacity X, you would rather have more people using it even if that means they can each use less.
    replies(1): >>43168074 #
    10. raylad ◴[25 Feb 25 03:18 UTC] No.43167719[source]▶
    The problem with the API is that it, as it says in the documentation, could cost $100/hr.

    I would pay $50/mo or something to be able to have reasonable use of Claude Code in a limited (but not as limited) way as through the web UI, but all of these coding tools seem to work only with the API and are therefore either too expensive or too limited.

    replies(1): >>43167844 #
    11. rudedogg ◴[25 Feb 25 03:33 UTC] No.43167844[source]▶
    > The problem with the API is that it, as it says in the documentation, could cost $100/hr.

    I've used https://github.com/cline/cline to get a similar workflow to their Claude Code demo, and yes it's amazing how quickly the token counts add up. Claude seems to have capacity issues so I'm guessing they decided to charge a premium for what they can serve up.

    +1 on the too expensive or too limited sentiment. I subscribed to Claude for quite a while but got frustrated the few times I would use it heavily I'd get stuck due to the rate limits.

    I could stomach a $20-$50 subscription for something like 3.7 that I could use a lot when coding, and not worry about hitting limits (or I suspect being pushed on to a quantized/smaller model when used too much).

    replies(1): >>43172588 #
    12. brador ◴[25 Feb 25 04:07 UTC] No.43168074{6}[source]▶
    If you can’t scale with your customer base fire your CTO.
    13. jasonjmcghee ◴[25 Feb 25 14:52 UTC] No.43172588{3}[source]▶
    Claude Code does caching well fwiw. Looking my costs after a few code sessions (totaling $6 or so) the vast majority is cache read, which is great to see. Without caching it'd be wildly more expensive.

    Like $5+ was cache read ($0.05/token vs $3/token) so it would have cost $300+