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. google is broken...

google is broken...

Scheduled Pinned Locked Moved Uncategorized
26 Posts 9 Posters 0 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.
  • oppen@merveilles.townO oppen@merveilles.town

    @liaizon In $dayjob we have an elusive bug in our impl. of Android's MediaSession/ExoPlayer. Having previously spent days trying to fix it I thought I'd try the Claude account we're testing, let's see if the AI can find the problem... it's very very confidentlly identified the issue in 3 or 4 places so far, none of the fixes it's added have worked at all, but the language it uses is so matter of fact. It's a user-facing issue and the in-app radio playback locks up until restart, so big problem when it happens, the 1st time Claude said it knew what the issue was I was momentarily very happy...

    liaizon@social.wake.stL This user is from outside of this forum
    liaizon@social.wake.stL This user is from outside of this forum
    liaizon@social.wake.st
    wrote last edited by
    #13

    @oppen it so often being confidently wrong is one of the most annoying aspects of this jank for sure. I think many people would respond better to a bunch more of "I don't know!" responses littered in (it could probably just be randomized) just to have less certainty...

    1 Reply Last reply
    0
    • liaizon@social.wake.stL liaizon@social.wake.st

      amazing how jank this all is

      Link Preview Image
      despens@post.lurk.orgD This user is from outside of this forum
      despens@post.lurk.orgD This user is from outside of this forum
      despens@post.lurk.org
      wrote last edited by
      #14

      @liaizon Perfect comedy! Really digging the references on this one:

      Link Preview Image
      liaizon@social.wake.stL 1 Reply Last reply
      0
      • despens@post.lurk.orgD despens@post.lurk.org

        @liaizon Perfect comedy! Really digging the references on this one:

        Link Preview Image
        liaizon@social.wake.stL This user is from outside of this forum
        liaizon@social.wake.stL This user is from outside of this forum
        liaizon@social.wake.st
        wrote last edited by
        #15

        @despens its amazing to see how everytime google uses citations they are basically randomly added later. like it makes up some shit, then "cites" it by just showing a link that contains a single word of your search.

        despens@post.lurk.orgD 1 Reply Last reply
        0
        • liaizon@social.wake.stL liaizon@social.wake.st

          @despens its amazing to see how everytime google uses citations they are basically randomly added later. like it makes up some shit, then "cites" it by just showing a link that contains a single word of your search.

          despens@post.lurk.orgD This user is from outside of this forum
          despens@post.lurk.orgD This user is from outside of this forum
          despens@post.lurk.org
          wrote last edited by
          #16

          @liaizon 👆 This post of yours is actually a prompt that forms the foundation of a billion dollar business

          1 Reply Last reply
          0
          • liaizon@social.wake.stL liaizon@social.wake.st

            amazing how jank this all is

            Link Preview Image
            gub@framapiaf.orgG This user is from outside of this forum
            gub@framapiaf.orgG This user is from outside of this forum
            gub@framapiaf.org
            wrote last edited by
            #17

            @liaizon
            The correct answer is 3.
            "Rassemblement National"

            1 Reply Last reply
            0
            • liaizon@social.wake.stL liaizon@social.wake.st

              amazing how jank this all is

              Link Preview Image
              fluchtkapsel@nerdculture.deF This user is from outside of this forum
              fluchtkapsel@nerdculture.deF This user is from outside of this forum
              fluchtkapsel@nerdculture.de
              wrote last edited by
              #18

              @liaizon missed opportunity, Google, missed opportunity.

              Link Preview Image
              liaizon@social.wake.stL 1 Reply Last reply
              0
              • fluchtkapsel@nerdculture.deF fluchtkapsel@nerdculture.de

                @liaizon missed opportunity, Google, missed opportunity.

                Link Preview Image
                liaizon@social.wake.stL This user is from outside of this forum
                liaizon@social.wake.stL This user is from outside of this forum
                liaizon@social.wake.st
                wrote last edited by
                #19

                @fluchtkapsel its impressive how consistent this "bug" is, like they have to realize it by now. I wonder what the internal Google chat looksike atm

                1 Reply Last reply
                0
                • liaizon@social.wake.stL liaizon@social.wake.st

                  amazing how jank this all is

                  Link Preview Image
                  liaizon@social.wake.stL This user is from outside of this forum
                  liaizon@social.wake.stL This user is from outside of this forum
                  liaizon@social.wake.st
                  wrote last edited by
                  #20

                  someone at google is still alive!

                  Link Preview Image
                  s_ol@merveilles.townS 1 Reply Last reply
                  1
                  0
                  • liaizon@social.wake.stL liaizon@social.wake.st

                    someone at google is still alive!

                    Link Preview Image
                    s_ol@merveilles.townS This user is from outside of this forum
                    s_ol@merveilles.townS This user is from outside of this forum
                    s_ol@merveilles.town
                    wrote last edited by
                    #21

                    @liaizon
                    the sad thing is that they can (and might) fix this, but the fix will be one of these two:

                    1. have the model run much longer, then have another model read that output and summarize: "reasoning" (aka maximize resource burning)
                    2. give the AI a traditionally-implemented "count characters in word" tool (address the symptom, aka admit defeat.

                    liaizon@social.wake.stL s_ol@merveilles.townS mntmn@mastodon.socialM 3 Replies Last reply
                    0
                    • s_ol@merveilles.townS s_ol@merveilles.town

                      @liaizon
                      the sad thing is that they can (and might) fix this, but the fix will be one of these two:

                      1. have the model run much longer, then have another model read that output and summarize: "reasoning" (aka maximize resource burning)
                      2. give the AI a traditionally-implemented "count characters in word" tool (address the symptom, aka admit defeat.

                      liaizon@social.wake.stL This user is from outside of this forum
                      liaizon@social.wake.stL This user is from outside of this forum
                      liaizon@social.wake.st
                      wrote last edited by
                      #22

                      @s_ol it should be doing tool calls anyway for many questions. Like Google search used to do basic math and equations inline without searching.

                      1 Reply Last reply
                      0
                      • s_ol@merveilles.townS s_ol@merveilles.town

                        @liaizon
                        the sad thing is that they can (and might) fix this, but the fix will be one of these two:

                        1. have the model run much longer, then have another model read that output and summarize: "reasoning" (aka maximize resource burning)
                        2. give the AI a traditionally-implemented "count characters in word" tool (address the symptom, aka admit defeat.

                        s_ol@merveilles.townS This user is from outside of this forum
                        s_ol@merveilles.townS This user is from outside of this forum
                        s_ol@merveilles.town
                        wrote last edited by
                        #23

                        @liaizon
                        i was under the impression that other general-purpose models have solved this and would've guessed they implemented option 2 but actually chatgpt is still confidently wrong (now with sources!)

                        Link Preview Image
                        liaizon@social.wake.stL 1 Reply Last reply
                        0
                        • s_ol@merveilles.townS s_ol@merveilles.town

                          @liaizon
                          i was under the impression that other general-purpose models have solved this and would've guessed they implemented option 2 but actually chatgpt is still confidently wrong (now with sources!)

                          Link Preview Image
                          liaizon@social.wake.stL This user is from outside of this forum
                          liaizon@social.wake.stL This user is from outside of this forum
                          liaizon@social.wake.st
                          wrote last edited by
                          #24

                          @s_ol I love how all these companies are completely ruining the concept of souces and citations

                          1 Reply Last reply
                          0
                          • s_ol@merveilles.townS s_ol@merveilles.town

                            @liaizon
                            the sad thing is that they can (and might) fix this, but the fix will be one of these two:

                            1. have the model run much longer, then have another model read that output and summarize: "reasoning" (aka maximize resource burning)
                            2. give the AI a traditionally-implemented "count characters in word" tool (address the symptom, aka admit defeat.

                            mntmn@mastodon.socialM This user is from outside of this forum
                            mntmn@mastodon.socialM This user is from outside of this forum
                            mntmn@mastodon.social
                            wrote last edited by
                            #25

                            @s_ol @liaizon last night when i tried exactly this, it was already using python to count chars, but only sometimes. when i asked "how many p in paraphernalia" it said 3. so it's just very random

                            liaizon@social.wake.stL 1 Reply Last reply
                            0
                            • mntmn@mastodon.socialM mntmn@mastodon.social

                              @s_ol @liaizon last night when i tried exactly this, it was already using python to count chars, but only sometimes. when i asked "how many p in paraphernalia" it said 3. so it's just very random

                              liaizon@social.wake.stL This user is from outside of this forum
                              liaizon@social.wake.stL This user is from outside of this forum
                              liaizon@social.wake.st
                              wrote last edited by
                              #26

                              @mntmn @s_ol how many pythons does it take to change a lightbulb?

                              1 Reply Last reply
                              0
                              • dantescanline@autonomous.zoneD dantescanline@autonomous.zone shared this topic
                              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