Tag: Marco Arment

  • Clone Wars Watchlist

    I have a tiny Kickstarter problem, but I mostly manage to resist. Earlier this year my excitement for backing video games overwhelmed me a bit, as you can see. I’m excited especially for The Banner Saga, but like any preorder, I’m out money now for something I won’t have for a year.

    As you may know, I am also a big fan of the 5by5 podcast network, including the show Build & Analyze with Marco Arment. A few months ago, I wrote in to the show with this question:

    I’m wondering if you’d talk about the recent large-scale Kickstarter video game projects, such as Double Fine Adventure, Wasteland 2, and Banner Saga. Do you think this would be a way fund non-game apps?

    Marco and Dan answered this in Episode #70, 116 Degree Burns, starting at the 23:35 mark, right after the first sponsor, and going to about 34:25. I meant to follow-up a while ago, but the end of the semester was a busy time, so here goes.

    My interpretation of Marco’s overall point was that software, especially complex apps like a game, is too risky to back. This is because it’s near impossible to estimate the total amount of development time, and therefore the cost, so the project can’t set a reasonable goal or backer rewards.

    As a fellow software engineer, I totally understand this difficulty, but Marco’s take was definitely a downer for me. I think I wanted him to agree with my thinking, which is that Kickstarter could be an alternative source of funding for app creators, basically a way to gauge market interest before doing anything more than preliminary planning and development. I think Marco goes too far in claiming that Kickstarter possibly shouldn’t allow these projects because of that risk.

    As an aside, there is some irony in one of the first high-profile app Kickstarter projects, Dark Sky, being an occasional sponsor on 5by5.

    Kickstarter has a good stats page, but it just shows the breakdown of successful vs. unsuccessful funding; it doesn’t show how successful projects are at completion and wisely using their funding, which is at the core of Marco’s argument. At a glance,  I have seen a few updates from some of the projects I’ve backed that the project team didn’t accurately predict the cost and effort of putting together (and in some cases, shipping) backer rewards. I do note that Games as a category are on the higher end of the money range, but the lower end of the success rate, which probably bears out Marco’s point about risk.

    That all said, I think Kickstarter has a very important role for the future of “the useful arts”. The content industry in particular is in the process of a major upheaval, so it’s not clear how someone with a good idea that doesn’t fit into the usual day job archetype can get the money they need upfront in order to take the time to create. Backers can in that sense collectively fill the role of Renaissance patrons.

    Apps are in a bit different category, in no small part because the skills necessary to create an app are economically valued in the traditional employment market. Maybe some of my interest in the idea is that, while I love my job, I envy some aspects of Marco’s lifestyle as an independent app developer. (It doesn’t help that we’re within a few months of the same age.) I suppose then a subtext of my question was wondering if this is a feasible way to start working in this space.

    What do you think?

  • Sunspot

    A small Yorkshire Terrier lies in a pet bed on a green upholstered chair in a sunny living room.

    I wish I could nap like Pike naps.

  • The Muppets Meet Murderbot

    For the last year and a half or so Andrle and I have been having a ton of fun as part of an online book club put together by my friend Tanya. Unlike most book clubs where you all read the same thing, we all just share things we love that we’ve been reading.

    One recommendation that kept coming up was The Murderbot Diaries by Martha Wells, and I’m glad we finally ran with it and started reading them. We’ve been bingeing the last few weeks and they’re really, really great. Highly recommend (even though I’m only on Book 4.)

    Unsurprisingly another thing I’ve been reading about and thinking about a lot is the advent of Large Language Models, particularly as manifested by ChatGPT. My past work life as an NLP practitioner has me a mix of curious, envious, and highly suspicious of what these are and how they’re being used. In the short term I don’t mind using them as a toy that I can play with for the purpose of a joke, which is what this post is about.

    A recurring topic in this book club is how we might have the Muppets interpret a particular book, or how we might recast a movie with Muppets (but keep one human actor). This provides a lot of fun discussions, especially since I grew up regularly watching the classic Muppet movies on VHS recorded off of TV, and I really like musicals.

    That all brings me to some prompt iterating that I did to get ChatGPT to write the painfully cliché finale to a Muppet musical featuring Murderbot. (Apologies to both Henson and Wells.)

    Verse 1 (Murderbot):
    I used to be a killing machine,
    A rogue cyborg, feared and mean,
    But then I met the Muppets and Kermit,
    And learned what friendship truly meant.

    Verse 2 (Kermit):
    I'm just a simple frog, it's true,
    But I believe in friendship too,
    And when I met Murderbot, I knew,
    Together we could do something new.

    Chorus (All):
    We don't need to kill no more,
    Our friends are all we're fighting for,
    With Murderbot and Kermit side by side,
    We'll show the world what we stand for.

    Verse 3 (Murderbot):
    I never wanted to be a tool,
    But that's all humans see in me, it's cruel,
    I used to dream of breaking free,
    From their endless schemes and greed.

    Verse 4 (Kermit):
    It's true, I'm always happy-go-lucky,
    But I've been through some tough times that were quite yucky,
    But now with Murderbot and the gang,
    I know our friendship will never hang.

    Chorus (All):
    We don't need to kill no more,
    Our friends are all we're fighting for,
    With Murderbot and Kermit side by side,
    We'll show the world what we stand for.

    The past is gone, the future bright,
    With friends like these, we'll win the fight,
    Our love and trust will guide us through,
    Together we'll see this journey through.

    Chorus (All):
    We don't need to kill no more,
    Our friends are all we're fighting for,
    With Murderbot and Kermit side by side,
    We'll show the world what we stand for.

    So let's raise our voices high,
    And let the world hear our battle cry,
    With Muppets and Murderbot side by side,
    We'll change the world and turn the tide.
    OpenAI. (2023, Mar. 16) [Iterative prompt conversation starting with “This Muppet movie is about a rogue cyborg traveling to different space stations and learning the power of friendship from the Muppets” and “I need some lyrics for the big finals. The music is big broadway style number about how the rogue cyborg doesn’t need to kill bad guys anymore because it has friends.” and then encouraging more dialogue between Kermit and Murderbot] https://chat.openai.com/

    Yes, I looked up recommendations on how to properly cite ChatGPT output.

    Overall the result was mildly amusing. I couldn’t get it to capture Murderbot’s signature style, presumably because while information about the novellas are in its model training, not enough text from the novellas are in there.

    I’m still not sure what useful things I could do with this kind of tool, but in the meantime, I can make it make silly songs.

  • Fox Ferocity

    Pike playing with a toy almost as big as he is.

  • Groomed Pike

    Tiny freshly groomed Yorkie sits on a teal couch wearing a monstera bow tie

    I love this little gentleman.

  • The Kale Wanter

    A small black and brown Yorkie stands on a cream rug in front of a brown cupboard begging for the bunch of lacinato kale in hand in the foreground.