Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • World
  • Users
  • Groups
Skins
  • Light
  • Brite
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (Cyborg)
  • No Skin
Collapse
Brand Logo

CIRCLE WITH A DOT

  1. Home
  2. Uncategorized
  3. hm https://github.com/bluesky-social/social-app/blob/main/CLAUDE.md

hm https://github.com/bluesky-social/social-app/blob/main/CLAUDE.md

Scheduled Pinned Locked Moved Uncategorized
108 Posts 55 Posters 289 Views
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • res260@infosec.exchangeR res260@infosec.exchange

    @erincandescent @cwebber I agree, I think a lot of people don't consider their code craft, but maybe the final product more so

    erincandescent@akko.erincandescent.netE This user is from outside of this forum
    erincandescent@akko.erincandescent.netE This user is from outside of this forum
    erincandescent@akko.erincandescent.net
    wrote last edited by
    #54
    @res260 @cwebber even a craftsman is sometimes just doing rote tasks
    fay@lingo.lolF 1 Reply Last reply
    0
    • cwebber@social.coopC cwebber@social.coop

      hm https://github.com/bluesky-social/social-app/blob/main/CLAUDE.md

      joeyh@sunbeam.cityJ This user is from outside of this forum
      joeyh@sunbeam.cityJ This user is from outside of this forum
      joeyh@sunbeam.city
      wrote last edited by
      #55

      @cwebber I found LLM generated code in vim today

      gnomon@mastodon.socialG 1 Reply Last reply
      0
      • cwebber@social.coopC cwebber@social.coop

        I mean when I check my feed much of the Bluesky eng team seems to be posting about how great Claude is all the time so I have been background wondering how common vibecoding is in that ecosystem

        kirakira@furry.engineerK This user is from outside of this forum
        kirakira@furry.engineerK This user is from outside of this forum
        kirakira@furry.engineer
        wrote last edited by
        #56

        @cwebber based on how well bsky tends to work i feel like this is likely

        1 Reply Last reply
        0
        • andymoose@fedi.aiga.rocksA andymoose@fedi.aiga.rocks

          @cwebber @kkarhan The most disappointing thing about AI (in the software development space) is how quickly and gleefully so-called senior engineers abandoned their craft for vibe coding.

          thebluewizard@masto.hackers.townT This user is from outside of this forum
          thebluewizard@masto.hackers.townT This user is from outside of this forum
          thebluewizard@masto.hackers.town
          wrote last edited by
          #57

          @andymoose @cwebber @kkarhan Disclaimer: I never use any LLM stuff, so I may be off base here.

          I have a thought about that!

          Imagine a scenario: Thanks to the layoff of developers thanks *dry tone* to the "insanely great" promise of LLM, there is now a lone developer vibecoding the main application for the company. Let's say he is doing well. But remember that he must feed a series of prompts, refining and growing the application as he progresses. Then he got a new job and left the company.

          ->

          thebluewizard@masto.hackers.townT 1 Reply Last reply
          0
          • thebluewizard@masto.hackers.townT thebluewizard@masto.hackers.town

            @andymoose @cwebber @kkarhan Disclaimer: I never use any LLM stuff, so I may be off base here.

            I have a thought about that!

            Imagine a scenario: Thanks to the layoff of developers thanks *dry tone* to the "insanely great" promise of LLM, there is now a lone developer vibecoding the main application for the company. Let's say he is doing well. But remember that he must feed a series of prompts, refining and growing the application as he progresses. Then he got a new job and left the company.

            ->

            thebluewizard@masto.hackers.townT This user is from outside of this forum
            thebluewizard@masto.hackers.townT This user is from outside of this forum
            thebluewizard@masto.hackers.town
            wrote last edited by
            #58

            @andymoose @cwebber @kkarhan The company then got a problem: Even after hiring a new developer (or two...who knows?), they can't figure out how the code work (no real documents) and, worse, the prompts the original developer wrote is not kept. IOW there is no "source code", so to speak. Disaster eventually strikes the company as a result.

            Ain't that wonderful, huh? *sarcastic tone*

            Multiply that by ten thousands of this scenario across various companies and we got a real economic crisis!

            END

            kkarhan@infosec.spaceK n_dimension@infosec.exchangeN tknarr@mstdn.socialT 3 Replies Last reply
            0
            • thebluewizard@masto.hackers.townT thebluewizard@masto.hackers.town

              @andymoose @cwebber @kkarhan The company then got a problem: Even after hiring a new developer (or two...who knows?), they can't figure out how the code work (no real documents) and, worse, the prompts the original developer wrote is not kept. IOW there is no "source code", so to speak. Disaster eventually strikes the company as a result.

              Ain't that wonderful, huh? *sarcastic tone*

              Multiply that by ten thousands of this scenario across various companies and we got a real economic crisis!

              END

              kkarhan@infosec.spaceK This user is from outside of this forum
              kkarhan@infosec.spaceK This user is from outside of this forum
              kkarhan@infosec.space
              wrote last edited by
              #59

              @thebluewizard @andymoose @cwebber And it's in our best interest for that to happen sooner than later so the fallout for everyone else is kept minimal...

              1 Reply Last reply
              0
              • thebluewizard@masto.hackers.townT thebluewizard@masto.hackers.town

                @andymoose @cwebber @kkarhan The company then got a problem: Even after hiring a new developer (or two...who knows?), they can't figure out how the code work (no real documents) and, worse, the prompts the original developer wrote is not kept. IOW there is no "source code", so to speak. Disaster eventually strikes the company as a result.

                Ain't that wonderful, huh? *sarcastic tone*

                Multiply that by ten thousands of this scenario across various companies and we got a real economic crisis!

                END

                n_dimension@infosec.exchangeN This user is from outside of this forum
                n_dimension@infosec.exchangeN This user is from outside of this forum
                n_dimension@infosec.exchange
                wrote last edited by
                #60

                @andymoose @cwebber @kkarhan @thebluewizard

                So yeah, that's what happens when you suck at vibecode

                1. Write a basic .MD file

                2. Part of the MD file is writing every delta into
                a ./DOCS and ./BACKUPS

                Not only you have every .release you can roll back in source code, but you have every delta in DOCS

                The folks who sucked at being a "real" programmer suck at #vibecode

                P. S. You don't read source code when you vibecode.
                Folks who "WAAAH BUT SAUCE KODE" never vibecoded.

                "Using AI is a learned skill"

                kkarhan@infosec.spaceK 1 Reply Last reply
                0
                • thebluewizard@masto.hackers.townT thebluewizard@masto.hackers.town

                  @andymoose @cwebber @kkarhan The company then got a problem: Even after hiring a new developer (or two...who knows?), they can't figure out how the code work (no real documents) and, worse, the prompts the original developer wrote is not kept. IOW there is no "source code", so to speak. Disaster eventually strikes the company as a result.

                  Ain't that wonderful, huh? *sarcastic tone*

                  Multiply that by ten thousands of this scenario across various companies and we got a real economic crisis!

                  END

                  tknarr@mstdn.socialT This user is from outside of this forum
                  tknarr@mstdn.socialT This user is from outside of this forum
                  tknarr@mstdn.social
                  wrote last edited by
                  #61

                  @thebluewizard @andymoose @cwebber @kkarhan And even if they had the prompts, that's no guarantee that the LLM will produce the same output if fed those prompts again. All they could depend on is the raw source code the original dev had generated, no matter how incomprehensible it is.

                  The sad part is the company won't blame LLMs for the situation, they'll blame the new devs for not being able to make things work.

                  kkarhan@infosec.spaceK 1 Reply Last reply
                  0
                  • n_dimension@infosec.exchangeN n_dimension@infosec.exchange

                    @andymoose @cwebber @kkarhan @thebluewizard

                    So yeah, that's what happens when you suck at vibecode

                    1. Write a basic .MD file

                    2. Part of the MD file is writing every delta into
                    a ./DOCS and ./BACKUPS

                    Not only you have every .release you can roll back in source code, but you have every delta in DOCS

                    The folks who sucked at being a "real" programmer suck at #vibecode

                    P. S. You don't read source code when you vibecode.
                    Folks who "WAAAH BUT SAUCE KODE" never vibecoded.

                    "Using AI is a learned skill"

                    kkarhan@infosec.spaceK This user is from outside of this forum
                    kkarhan@infosec.spaceK This user is from outside of this forum
                    kkarhan@infosec.space
                    wrote last edited by
                    #62

                    @n_dimension @andymoose @cwebber @thebluewizard Granted, "#VibeCoding" is just a different term to "bossing around #AI until it does 50% what it should do and calling that a success when a #Skiddie copypasting shit would've done a better job even when half the amount wasted on *"#AI" Tokens...

                    n_dimension@infosec.exchangeN 1 Reply Last reply
                    0
                    • tknarr@mstdn.socialT tknarr@mstdn.social

                      @thebluewizard @andymoose @cwebber @kkarhan And even if they had the prompts, that's no guarantee that the LLM will produce the same output if fed those prompts again. All they could depend on is the raw source code the original dev had generated, no matter how incomprehensible it is.

                      The sad part is the company won't blame LLMs for the situation, they'll blame the new devs for not being able to make things work.

                      kkarhan@infosec.spaceK This user is from outside of this forum
                      kkarhan@infosec.spaceK This user is from outside of this forum
                      kkarhan@infosec.space
                      wrote last edited by
                      #63

                      @tknarr @thebluewizard @andymoose @cwebber exactly that!

                      Cuz I've seen that shit even with "traditional IT".

                      • Ever had to "unfuck" a #ZFS on top of a Hardware-#RAID controller?
                        • If you know, you propably already run to the toilet to throw up, because one should not violate THE ONE RULE OF USING ZFS...

                      Never ever lie to ZFS!

                      1 Reply Last reply
                      0
                      • kkarhan@infosec.spaceK kkarhan@infosec.space

                        @n_dimension @andymoose @cwebber @thebluewizard Granted, "#VibeCoding" is just a different term to "bossing around #AI until it does 50% what it should do and calling that a success when a #Skiddie copypasting shit would've done a better job even when half the amount wasted on *"#AI" Tokens...

                        n_dimension@infosec.exchangeN This user is from outside of this forum
                        n_dimension@infosec.exchangeN This user is from outside of this forum
                        n_dimension@infosec.exchange
                        wrote last edited by
                        #64

                        @andymoose @cwebber @thebluewizard @kkarhan

                        "Bossing AI around" is actually a very good description of #vibecoding

                        I call it "Hitting the machine with a stick" (like a recalcitant) mule.

                        However, the accuracy is significantly better than 50%

                        Granted, #Ai will get into the weeds sometimes.

                        But because I was a shit programmer before Ai (slow and dim) Vibecoding makes me better.
                        There were times I would get stuck on a bug for a day, with Ai, I can mush it in 15 min max.

                        In my experience, majority of errors are regex or basic syntax, my Webby got carded last night because the Ai commented out whole anti-carding logic by accident, even though I got it to check it twice.

                        Each fuckup makes you write better prompts.

                        kkarhan@infosec.spaceK 1 Reply Last reply
                        0
                        • n_dimension@infosec.exchangeN n_dimension@infosec.exchange

                          @andymoose @cwebber @thebluewizard @kkarhan

                          "Bossing AI around" is actually a very good description of #vibecoding

                          I call it "Hitting the machine with a stick" (like a recalcitant) mule.

                          However, the accuracy is significantly better than 50%

                          Granted, #Ai will get into the weeds sometimes.

                          But because I was a shit programmer before Ai (slow and dim) Vibecoding makes me better.
                          There were times I would get stuck on a bug for a day, with Ai, I can mush it in 15 min max.

                          In my experience, majority of errors are regex or basic syntax, my Webby got carded last night because the Ai commented out whole anti-carding logic by accident, even though I got it to check it twice.

                          Each fuckup makes you write better prompts.

                          kkarhan@infosec.spaceK This user is from outside of this forum
                          kkarhan@infosec.spaceK This user is from outside of this forum
                          kkarhan@infosec.space
                          wrote last edited by
                          #65

                          @n_dimension @andymoose @cwebber @thebluewizard I still think it's #WastefulComputing and doesn't really help oneself to become better at coding.

                          • Or not even better at reviewing and testing.
                          • At best it'll make one better at documenting requirements.
                            • Basically doing a shitty way to learn "Requirements Engineering"...
                          1 Reply Last reply
                          0
                          • cwebber@social.coopC cwebber@social.coop

                            I mean when I check my feed much of the Bluesky eng team seems to be posting about how great Claude is all the time so I have been background wondering how common vibecoding is in that ecosystem

                            dcoderlt@ohai.socialD This user is from outside of this forum
                            dcoderlt@ohai.socialD This user is from outside of this forum
                            dcoderlt@ohai.social
                            wrote last edited by
                            #66

                            @cwebber
                            Bit of a tangent, but a few months ago, when tech nerds on bsky and fedi started talking about Framework being a milkshake duck, Bsky staff immediately started bragging how cool and fast and powerful their Frameworks are.

                            1 Reply Last reply
                            0
                            • res260@infosec.exchangeR res260@infosec.exchange

                              @erincandescent @cwebber I agree, I think a lot of people don't consider their code craft, but maybe the final product more so

                              benjamineskola@hachyderm.ioB This user is from outside of this forum
                              benjamineskola@hachyderm.ioB This user is from outside of this forum
                              benjamineskola@hachyderm.io
                              wrote last edited by
                              #67

                              @res260 @erincandescent @cwebber if you care about the final product, surely you should care about how it’s made?

                              I see so many apologists for LLM usage recently trying to distinguish between the outcome and the process, as if the quality of the outcome isn’t defined by the process.

                              erincandescent@akko.erincandescent.netE 1 Reply Last reply
                              0
                              • benjamineskola@hachyderm.ioB benjamineskola@hachyderm.io

                                @res260 @erincandescent @cwebber if you care about the final product, surely you should care about how it’s made?

                                I see so many apologists for LLM usage recently trying to distinguish between the outcome and the process, as if the quality of the outcome isn’t defined by the process.

                                erincandescent@akko.erincandescent.netE This user is from outside of this forum
                                erincandescent@akko.erincandescent.netE This user is from outside of this forum
                                erincandescent@akko.erincandescent.net
                                wrote last edited by
                                #68
                                @benjamineskola @res260 @cwebber is this an argument of quality or of morals?

                                Because morals.. people can have different views on. But quality is very much about the end result
                                airtower@woem.menA 1 Reply Last reply
                                0
                                • erincandescent@akko.erincandescent.netE erincandescent@akko.erincandescent.net
                                  @benjamineskola @res260 @cwebber is this an argument of quality or of morals?

                                  Because morals.. people can have different views on. But quality is very much about the end result
                                  airtower@woem.menA This user is from outside of this forum
                                  airtower@woem.menA This user is from outside of this forum
                                  airtower@woem.men
                                  wrote last edited by
                                  #69

                                  @erincandescent@akko.erincandescent.net @benjamineskola@hachyderm.io @res260@infosec.exchange @cwebber@social.coop If the thing isn't "make once and forget" the process is very much part of quality, because it decides if the thing is maintainable.

                                  erincandescent@akko.erincandescent.netE 1 Reply Last reply
                                  0
                                  • airtower@woem.menA airtower@woem.men

                                    @erincandescent@akko.erincandescent.net @benjamineskola@hachyderm.io @res260@infosec.exchange @cwebber@social.coop If the thing isn't "make once and forget" the process is very much part of quality, because it decides if the thing is maintainable.

                                    erincandescent@akko.erincandescent.netE This user is from outside of this forum
                                    erincandescent@akko.erincandescent.netE This user is from outside of this forum
                                    erincandescent@akko.erincandescent.net
                                    wrote last edited by
                                    #70
                                    @airtower @res260 @benjamineskola @cwebber two projects with identical code are, modulo institutional knowledge, equally maintainable; would you disagree?
                                    benjamineskola@hachyderm.ioB 1 Reply Last reply
                                    0
                                    • erincandescent@akko.erincandescent.netE erincandescent@akko.erincandescent.net
                                      @airtower @res260 @benjamineskola @cwebber two projects with identical code are, modulo institutional knowledge, equally maintainable; would you disagree?
                                      benjamineskola@hachyderm.ioB This user is from outside of this forum
                                      benjamineskola@hachyderm.ioB This user is from outside of this forum
                                      benjamineskola@hachyderm.io
                                      wrote last edited by
                                      #71

                                      @erincandescent @res260 @cwebber @airtower

                                      'modulo institutional knowledge' is doing a lot of heavy lifting there since that's half the problem with LLM usage

                                      and the other half of the problem is the assumption that an LLM will produce identical code

                                      so I don't think there's a useful discussion to be had if those are your assumptions

                                      erincandescent@akko.erincandescent.netE airtower@woem.menA 2 Replies Last reply
                                      0
                                      • liaizon@social.wake.stL liaizon@social.wake.st

                                        @erincandescent @ryanrandall @cwebber its not the same Why. They both have photos of their real face on the internet I checked.

                                        davidgerard@circumstances.runD This user is from outside of this forum
                                        davidgerard@circumstances.runD This user is from outside of this forum
                                        davidgerard@circumstances.run
                                        wrote last edited by
                                        #72

                                        @liaizon @erincandescent @ryanrandall @cwebber this is the one from the mirror universe

                                        1 Reply Last reply
                                        0
                                        • corujosilva@fedi.latC corujosilva@fedi.lat

                                          @cwebber before* any judgement on whethe it is a good thing or not, it was expected, tbh. it is very much on brand from their team.
                                          they always had the "tech enthusiast" ethos

                                          *just before.

                                          davidgerard@circumstances.runD This user is from outside of this forum
                                          davidgerard@circumstances.runD This user is from outside of this forum
                                          davidgerard@circumstances.run
                                          wrote last edited by
                                          #73

                                          @corujosilva @cwebber the team started as coiners, so they were very hot for AI

                                          1 Reply Last reply
                                          0
                                          Reply
                                          • Reply as topic
                                          Log in to reply
                                          • Oldest to Newest
                                          • Newest to Oldest
                                          • Most Votes


                                          • Login

                                          • Login or register to search.
                                          • First post
                                            Last post
                                          0
                                          • Categories
                                          • Recent
                                          • Tags
                                          • Popular
                                          • World
                                          • Users
                                          • Groups