← Home Photos Archive About Reading Also on Micro.blog
  • Guess what I’m reading before bedtime tonight?! Video Generation Models as World Simulators Might as well understand how this all works. 🚀

    → 6:52 PM, Feb 15
  • I KNEW Google’s 1M token claim was because OpenAI was about to drop something incredible. I did not expect this: Sora: Text-to-video 🥳

    → 11:19 AM, Feb 15
  • Been waiting for this. Now all my virtual employees can virtually use ChatGPT as their virtual Slack. 🤖😎

    → 12:17 PM, Jan 30
  • I heard JK (my old boss) made a prediction that animation would suffer 90% job loss due to AI. Then I found the video. Animation peeps: don’t base your existential crisis on someone who claims “prompting” is a thing. It’s not.

    → 11:07 AM, Jan 29
  • The deadline for Converge 2 (OpenAI’s $1m startup fund) is this evening. And while I would usually jump at the chance, there is this whole other world out there where the only backing you need are your customers. The pastures of the quiet 🦄 are lush and green–and open to everyone.☀️

    → 11:23 AM, Jan 26
  • Building Hollywood's Version of ChatGPT

    Wired covers Subtxt–without knowing about Subtxt:

    First, generative AI will eventually be a valuable tool in some creative realms, potentially including script writing, but only if the AI has been built from the ground up for that task.

    That would be the app I started building six years ago.

    Second, the flaws of today’s generative AIs make them unsuitable for serious work, especially in creative fields. General purpose AIs, like ChatGPT, are trained on whatever content the creator can steal on the internet, which means their output often consists of nonsense dressed up to appear authoritative. The best they can do is imitate their training set. These AIs will never be any good at creating draft scripts—even of the most formulaic programming—unless their training set includes a giant library of Hollywood scripts.

    The first part of this is right–the second part is woefully wrong.

    Training LLMs on scripts will just result in a preponderance of badly-written, meaningless screenplays.

    Training LLMs on a narrative framework that predicts a sequence of events that align with artistic intention and meaning?

    That’s the only way forward.

    → 3:55 PM, Jul 19
  • AI-Driven Efficiency: The Magic of Transmuting Support Queries into Blogs for a Solopreneur

    As a solopreneur, the addition of AI to my work has unlocked massive productivity for me. Transforming support requests into documentation which are then transmutated into blog posts will never not seem like pure magic to me.

    For instance, I received this request about an hour ago about why Muse was getting parts of the Storyform “wrong.” Turns out, GPT sometimes takes narrative concepts too literally.

    I answered the question using ChatGPT, where I just conversationally typed out my thinking behind it, and why that’s happening, etc. GPT-4 took those ideas, wrapped them up in a nice email response, which I then used to reply in HelpScout.

    Knowing this would likely help others, I just asked Chat to re-write the email as a page in the documentation. Took about 30 seconds to write, 15 seconds to push to GitHub, and about a minute for Netlify to re-render the whole thing. It’s here at the bottom: Subtxt-Muse: Best Practices for Storytellers - the section labeled “When Muse Gets It Wrong.”

    As it related to a couple of posts I just did on the Discord community earlier this morning, I went ahead and copied and pasted those into Chat, and asked it to turn it into a blog post. A couple of minutes later, the whole thing was live on my company’s blog: Adaptive Storyforming: Changing Story Structure on the Fly with AI.

    Prior to AI, this process would have taken minimum three hours, and by the end I would have been too exhausted to write anything about it.

    Now, I have time to write up this quick post. 😊

    I use this technique throughout everything I do now, and can’t imagine developing an app like Subtxt without it. 🚀

    → 1:40 PM, May 30
  • Leaked paper on “moats” and AI and how there’s no way what you build will remain a secret, nor will your models be a strategic advantage. Goes for those studios building out their AI🤫. It’s you and who you are that attracts your audience (i.e., your artists) not your IP.

    → 11:56 AM, May 4
  • My first documentation success story. While I was sleeping somebody needed help abd they were able to get the answer just by reading The Manual.

    This only encourages me to do more!

    → 8:21 AM, Jun 15
  • Bingo! Back in business on Monterey, looking dark and moody for the rest of the summer. 🌞🕶

    → 8:35 PM, Jun 11
  • A primer on Cryptoart and NFTs, if you’re like me and woke up this morning not having a clue either existed.

    → 12:04 PM, Feb 18
  • First week of work with the M1 MBA: def sticking with the Air for my mobile future. LOVE the lack of a fan and the ultra light design. Totally different creative choices with a computer this small. A sizable difference in my art.

    → 10:52 PM, Nov 20
  • Subscribing to Moretex is a no-brainer. First podcast I’m willing to sponsor without a second thought. Quality conversation for years.

    → 4:07 PM, Jul 23
  • The wider iPhone is a no-brainer. When reading, I always wish there was just slightly more room on either side.

    Same with Navy Blue. (With matching Watch of course)

    → 8:31 PM, Jun 28
  • Ok, I thought raising my wrist to activate Siri was cool enough…but now I just have to say the word while walking around the house with AirPods Pro in?! Don’t have to look at my watch or pull out the phone. Awesome upgrade.

    → 5:14 PM, Dec 27
  • I had no idea this was a thing! Click the dinosaur and now you have something to do while you’re waiting to connect.

    → 12:52 PM, Nov 27
  • Netlify is ridiculously simple and well thought out. Adding redirects took about 2 seconds.

    → 12:23 PM, Nov 19
  • Really enjoying JAMStack Radio. Can’t believe it started in 2016, and I’m just now getting into it!

    → 6:27 PM, Nov 13
  • Currently imagining how awesome it’s going to be to do what I love on a new MacBook Pro.

    → 11:17 AM, Nov 13
  • Just tried out Overdub for Descript. Basically, you screw up a word or words in your podcast, and you can TYPE replacement words. A Voice Double–tunes to your voice–replaces your original audio seamlessly! My first couple of tests right now were like magic.

    Now if I could only do the same with this travesty that is the latest version of Star Wars on Disney+!

    → 4:16 PM, Nov 12
  • Continuous deployment is the greatest thing in the world. Also, branch deploys for automatic staging servers. Netlify, I love you.

    → 5:29 PM, Nov 9
  • Trying Sizzy out, because there’s nothing I love more than new developer tools. (They’re site is beautiful too, insta-buy).

    → 5:52 PM, Nov 7
  • Nuxt JS is essentially the Laravel of Vue JS (which I get is a framework of a framework of JavaScript). Having spent a couple years mixing PHP and JS, I can easily say that Nuxt is the greatest developer experience by far.

    Completely intuitive and well thought-out.

    This presentation by the creator of Nuxt is a good start.

    → 11:18 PM, Nov 5
  • This is why I switched from PHP/Laravel to JAMStack…

    The old version of Narrative First:

    The new JAMStack-ified version of the same exact site:

    Oh. And the first Narrative First is the Lighthouse score on local.

    → 4:00 PM, Nov 1
  • Clicking Netlify’s Verify DNS Configuration over and over again like its the Apple store on iPhone night. 😁

    → 12:01 AM, Oct 31
  • It is ridiculous how effortless it is to spin up a static site with Netlify and JAMStack.

    There’s no way I’m going back to anything else.

    → 6:09 PM, Oct 29
  • An overwhelmingly insight post on Superhuman’s on-boarding and the delight with which they infuse everything. Looking to copy a lot of this once I finish engineering some key delight into Subtext.

    → 10:42 PM, Oct 24
  • There can be no greater than feeling, than the feeling one gets when you finally roll out an accelerated, hyper-realized version of your app WITHOUT ERRORS!

    Everything is possible!

    → 6:56 PM, Oct 24
  • This garage tour of Google circa 1998 is just what I needed this week:

    → 11:27 AM, Oct 24
  • Also, yesterday’s AWS debacle forced me to finally integrate 13 years of blog parts and articles into my app for writing stories, Subtext.

    Story structure nirvana, to be sure. And it’s nice to finally see something I imagined for over a decade finally come together.

    Let’s hope Amazon got its act together while I was sleeping.

    → 8:52 AM, Oct 23
  • Feels amazing to finally finish this first stage of rewriting Subtext. No more page refreshes. Search is blazingly fast. Key bindings to keep the writer in the moment. InstantScene offering meaningful writing prompts. So crazy how fun this is to develop.

    Rolling it out for testers this weekend. 😂

    → 10:25 PM, Oct 18
  • Have to keep reminding myself–when server charges go up, that’s a GOOD thing :) Means more and more people coming to your site and using your app. Never seen a bill this big before!

    → 10:24 AM, Oct 1
  • Started playing around with the new Descript, bringing the podcast back to life. While it doesn’t look like I have access to Overdub yet, the auto-transcript is about 10,000 times better than it was last year. Less time fixing bad interpretations.

    → 4:55 PM, Sep 25
  • Edit Your Voice by Typing

    Ok. This is just about the coolest thing I have ever heard of in a podcast app:

    With Overdub, you can make editorial corrections to your voice recordings by simply typing the words, and then we use AI to synthesize audio of your voice and blend it in seamlessly.

    Makes me want to start up the ‘ol podcast just to try it out 🤓

    → 8:34 AM, Sep 18
  • Loving my new watch face, courtesy of Grey Industries and the greatest podcast. Never thought to turn off the corners, and Better Day is a great visualization (one on the left). Swapped out his timer for the Sundial viz on the bottom. I like to know halftime for the day.

    → 11:43 AM, Apr 24
  • RSS
  • JSON Feed
  • Micro.blog