Most active commenters

    ←back to thread

    A staff engineer's journey with Claude Code

    (www.sanity.io)
    548 points kmelve | 11 comments | 02 Sep 25 19:34 UTC | HN request time: 1.21s | source | bottom
    Show context
    rhubarbtree ◴[03 Sep 25 06:33 UTC] No.45112846[source]▶
    Does anyone have a link to a video that uses Claude Code to produce clean robust code that solves a non trivial problem (ie not tic tac toe or a landing page) more quickly than a human programmer can write? I don’t want a “demo”, I want a livestream from an independent programmer unaffiliated with any AI company and thus not incentivised to hype.

    I want the code to have subsequently been deployed in production and demonstrably robust, without additional work outside of the livestream.

    The livestream should include code review, test creation, testing, PR creation.

    It should not be on a greenfield project, because nearly all coding is not.

    I want to use Claude and I want to be more productive, but my experience to date is that for writing code beyond autocomplete AI is not good enough and leads to low quality code that can’t be maintained, or else requires so much hand holding that it is actually less efficient than a good programmer.

    There are lots of incentives for marketing at the grassroots level. I am totally open to changing my mind but I need evidence.

    replies(27): >>45112915 #>>45112951 #>>45112960 #>>45112964 #>>45112968 #>>45112985 #>>45112994 #>>45113041 #>>45113054 #>>45113123 #>>45113184 #>>45113229 #>>45113316 #>>45113448 #>>45113465 #>>45113643 #>>45113677 #>>45113802 #>>45114193 #>>45114454 #>>45114485 #>>45114519 #>>45115642 #>>45115900 #>>45116522 #>>45123605 #>>45125152 #
    1. izacus ◴[03 Sep 25 07:03 UTC] No.45113022[source]▶
    People live stream their work all the time, it's really not unreasonable to ask for an example/tutorial on how to use the technology in the real world.
    replies(2): >>45113076 #>>45113278 #
    2. troupo ◴[03 Sep 25 07:03 UTC] No.45113030[source]▶
    > You want someone to spend their time to live-stream their codebase and them working on it using Claude code, which will then make it into production, going through all the processes on a non-greenfield project just so you can be convinced that it is worth it

    Why not? Plenty of people stream their work that later makes into production. Gaming community for example has no end of people building their games publicly.

    And yet, for all the "amazing one-shot capabilities that obviate the need for programmers" no one streams working with any of the AI tools.

    All we have is unverifiable claims like yours.

    replies(1): >>45113249 #
    3. mattmanser ◴[03 Sep 25 07:05 UTC] No.45113036[source]▶
    Firstly the OP asked has anyone done it, not will they do it.

    Secondly, extraordinary claims require extraordinary evidence.

    replies(1): >>45113538 #
    4. ochronus ◴[03 Sep 25 07:09 UTC] No.45113058[source]▶
    I think you completely missed the original point :/
    5. Kiro ◴[03 Sep 25 07:12 UTC] No.45113076[source]▶
    The people live streaming their work is a minuscule percentage of all programmers. And you can ask but the incentive to make such a video is not there unless you're selling an AI product yourself, which reduces the sample even more.
    6. thecupisblue ◴[03 Sep 25 07:46 UTC] No.45113249[source]▶
    >amazing one-shot capabilities that obviate the need for programmers

    "Amazing one-shot capabilities" is not the same as "an extremely useful tool that saves a ton of time"

    replies(1): >>45113326 #
    7. thecupisblue ◴[03 Sep 25 07:51 UTC] No.45113278[source]▶
    Yes, people who are:

    - Working on hobby projects/sideprojects

    - Working on open-source projects

    - Selling stuff

    For someone to create this example, they would either have to do it in a codebase they don't have problem open sourcing or which is open source, so they do not break NDA's and divulge company info/source code.

    How many people are ready to do that?

    The conditions of the OP are:

    - No demo, independent programmer

    - Non-greenfield project

    - Non-trivial problem

    - Code deployed in production and robust

    - Code review, test, testing, PR creation

    - Person be willing to live-stream their work and code while building

    Which is a pretty unreasonable set of conditions to prove "it works", when the person could read a tutorial and try it themselves.

    replies(1): >>45113362 #
    8. troupo ◴[03 Sep 25 08:00 UTC] No.45113326{3}[source]▶
    So where are all the streams using this "extremely useful tools that saves a lot of time"?

    If it's as useful or saving a lot of time, it would be a no brainer for people who build in public to use this tool, right?

    9. rhubarbtree ◴[03 Sep 25 08:07 UTC] No.45113362{3}[source]▶
    I’m happy for it to be on OSS, so long as that software is reasonably well known (ie user base is not a handful of people) and is used in production.
    replies(1): >>45114191 #
    10. ochronus ◴[03 Sep 25 08:42 UTC] No.45113538[source]▶
    This.
    11. newswasboring ◴[03 Sep 25 10:35 UTC] No.45114191{4}[source]▶
    What difference does it make how many people use it? Complex software exists all over the world for handful of users. I personally work in an industry where anything we create will be used by at max 100 people worldwide. Does it diminish the complexity of code? I think not.