sangsara.net

  • Week 48.23

    Week 48.23

    962 words

    Some things I asked the internet/AI this week:

    • Why do people never rinse their mouths out after brushing their teeth in the movies?
    • Isn’t it misleading and bad for oral hygiene education if directors leave it out for pacing reasons?
    • What’s the recipe for a Vesper martini?
    • How might a wealthy Indonesian put their billions of IDR to work beyond investing? (asking for a friend, I swear)

    Aside: ‘Asking the internet’ used to be our go-to phrase, but in an era where AI might be the one answering, does the term need revising? We used to be able to say ‘asking the internet’ but what about when you’re really asking an AI? They live on the internet and were certainly trained on internet content, but the old definition meant looking up content and new replies created by people; what do we call it when the answers AI generated? Keeping in mind that these answers may well be wrong, and in ways different from how a human might be wrong, it doesn’t feel like we should use the same terms. Or maybe we’ll keep referring to any hive mind as the internet?

    Can I go a week without talking about AI? I think those days may be behind us.

    Even iA Writer, the Markdown text editor I use for these updates, released a new update with an AI-related feature. No, it’s not automatically finishing your sentences or summarizing your essays. They’re all about the writing experience and process, and so they’re embracing how people use ChatGPT as a writing assistant, but helping them to preserve their own authentic voices. Text pasted from ChatGPT can be visually differentiated from text you wrote yourself, so you can see the Frankensteinian stitches on your monster. It also saves this info in the metadata for provenance.

    This suggests that many users send text back and forth to ChatGPT so often that they end up forgetting which bits they wrote themselves, which isn’t a problem I’ve had so far, but going forward, who knows? It’s a good idea and one I’m glad they’re testing, but iA Writer has always been a niche tool for a certain kind of user. I thnk word processors with integrated AI are going to be so widely used and loved by the end of 2024 that no one will care about who did what part.

    ===

    I made and released a new GPT, a game called Chrono Quest where you go back in time to improve humanity’s chances of beating an alien invasion. You can read more about it in my post here, but there are many ways to succeed, limited only by your imagination and problem solving inclinations. As a kid playing text adventure games, I never thought I’d see the day they could write themselves as you played. It even creates illustrations along the way, although those aren’t strictly necessary.

    I’ve got some other game ideas I’ll probably get on soon over the Christmas break. OpenAI announced yesterday that the GPT “App Store” meant to open in November was being delayed until early 2024. I guess that gives me more time to learn.

    ===

    It’s not accurate to say I didn’t get anything during the Black Friday/Cyber Monday sales. Pixelmator Pro for Mac was 50% off, and I thought it was time I upgraded to it from regular ol’ Pixelmator, which I must have bought over ten years ago for personal use as a substitute for Photoshop. Those were the days of per-once, use-forever software. To the developers’ credit, Pixelmator Pro is still offered through that model, although their newest app, Photomator, prefers a subscription pricing plan. The latter just won Apple’s Mac App of the Year award, by the way.

    Pixelmator Pro is more than just a Photoshop-type editor now, it’s also a video and vector image editor, and comes with lots of templates for creating posters, logos, and so on. And like Photomator, it has useful ML-based features for correcting color, removing noise, and increasingly resolution of photos. These are pretty old-school and conservative by the standards of generative AI — see the recent development of Magnific AI, a tool confusingly billed as “upscaling” when it’s really closer to hallucination. It can subjectively improve the quality of photos by generating plausible (but inaccurate) pixels.

    Check out this “upscaling” of Tomb Raider 1.

    ===

    Stumbling into the New York jazz scene by accident, I found two jazz artists I’d like to recommend: Brandee Younger and Samara Joy. Both already have a couple of albums out.

    Younger is a harpist who blends genres and leans modern. You’ll hear some hip-hop production, and it’s really not what you think when you hear the word “harp”. Her new album is Brand New Life, and is apparently based on and inspired the work of legendary harpist Dorothy Ashby, who I was also ignorant of. This is a weird observation, but hear me out. The opening track, the previously unrecorded, Ashby-written piece You’re A Girl For One Man Only, has a haunting melodic fragment that I think I recognize from… the soundtrack of the Japanese game/anime Steins;Gate of all things?!

    Samara Joy is a much more traditional vocalist, but what an incredible instrument her voice is. I’ll leave a video of her covering Lush Life below and you’ll see what I mean. I’m about to put her Christmas EP, A Joyful Holiday, on and get some lunch. See y’all later.

    (This week’s featured image was taken at a new mall that’s sprung up in Holland Village this weekend. It’s disconcerting; the massive development has been hidden behind hoardings for the past few years, and now revealed, it’s an unexpected contrast to the other old buildings and shopfronts, like a bionic arm of mediocre high street brands slapped onto an aging body.)

  • Chrono Quest

    516 words

    A thrilling adventure through time to give humanity a fighting chance!

    Chrono Quest is an interactive fiction game, like the Choose-Your-Own-Adventure stories of old. There are occasional graphics generated by DALL•E, just like how those books would have illustrations every now and then. Unlike those books, it’s a GPT that writes a different story each time, one that responds to your inputs and imagination. You can stick to the provided multiple choice options, or respond freely with your own ideas.

    The set up: An alien invasion threatens earth, and recently discovered time travel technology is our only hope. You must go back in time to change history and prepare humanity to meet this challenge.

    Play Now with ChatGPT

    Things I’ve tried (mild spoilers): I’ve done some ridiculous things in this game. I’ve gone back to find Jesus and recorded a video message of him appealing to people of the future to work together against the invaders. I prevented Hitler from taking power by stealing his playbook and being an even bigger Hitler. I imbued primitive cavemen with modern human DNA, to accelerate our evolution (and found myself the dumbest and shortest man in the world upon my return to the future). I also stopped the Fall of Constantinople with Semtex plastic explosives, prevented the Library of Alexandria from burning by building a firebreak , and became Leonardo da Vinci’s best mate after stumbling into his workshop with a fake stab wound. My colleague Brian played it and beat the aliens by uniting the world under a single market economy and rewriting property laws.

    ===

    This is the first game I’ve made since the launch of custom GPTs a few weeks ago. I played a bunch of text adventures as a kid, and just with books versus movies, they can be more immersive and fun than AAA games made for millions of dollars.

    AI Dungeon blew my mind when it came out a few years ago, unstable and liable to forget or misunderstand context as it was, it fulfilled many childhood dreams by being a flexible “dungeon master” that could take a story almost anywhere you asked it to. Wanted to pull out a gun in a medieval story, or use diplomatic words to get out of a situation? It was up to you. That was three years ago and built on GPT-2. It’s now three years later, and anyone can make their own custom story/game powered by GPT-4 — with virtually every shortcoming of AI Dungeon solved. Stories are incredibly coherent, natural, and well written.

    You can use normal ChatGPT to play interactive fiction games, and the story of Chrono Quest was one of the first I experimented with earlier this year. You can have a pretty good time even with GPT-3.5! But the advantage of custom GPTs is that you can craft a game world and share it with other people to play, specifying a certain style, and keeping an element of surprise when it comes to how the game plays out and interacts with the player.

    I might make more, I don’t know! Your thoughts are welcome.

  • Week 47.23

    Week 47.23

    823 words

    Oof, this was a tiring week. Navigating change, physically recovering from a vaccine’s side effects, and having conversations about Christmas gifts, that shit will wear a blogger out. Helping me navigate all this was my astrology GPT, Co—Sign, who would tell me how to deal with challenging situations and to trust in my own nature, even if some decisions felt like bad ideas by other people’s standards.

    Of course, the week started off with more twists in the OpenAI management saga, which seems to have ended now with Sam and Greg back at the company, not at Microsoft, and the formation of a new board underway. This pleases me because OpenAI was a company/brand with significant momentum and destroying value of that sort for no good reason doesn’t sit well with me (this may or may not be a reference to something else happening in my life). I’m glad I won’t have to port my collection of GPTs to another product like Poe or whatever.

    I used Gen AI to bone up on Silicon Valley mind viruses like EA (effective altruism) and e/acc (effective accelerationism), which I’d kinda grokked in passing but not spent any time specifically reading up on. I have to say I feel myself falling in the accelerationist camp — given current world events, we’re not exactly proving ourselves a worthy species, so we may as well hasten our demise or salvation in every aspect from the upheaval of labor to economic principles. Incidentally bitcoin hit a new high for the year this week, going over $38,000 for a brief period.

    I’ve buried the lede, but AI voice recognition and synthesis technology has enabled my favorite gag of the year: this Chinese dubbing of Van Morrison performing Caravan with The Band. It’s sublime; a French chef’s French kiss. It caught me in a moment of weakness and I couldn’t watch the whole thing through because I was dying of laughter. Van shouting “turn your radio up” in Mandarin will live rent free in my head from this week forth. This video is so precious to me I’ve saved a copy on personal cloud storage just in case the tweet goes down.

    ===

    I was excited to hear that the Muji store in Plaza Singapura had reopened after an extensive renovation, now twice its original size and the largest in South-East Asia. We went down on the weekend to take a look, and it had things normally seen only in Japan: plants, bicycles, an embroidery service, renovation services, a wider range of furnishings, frozen food, and regional specialty goods (including $350 silk scarves). Not your average Muji! In fact, it’s billed as a “Global Flagship Store”, and I hope their gamble pays off and Singaporeans vote for more of this with their wallets.

    ===

    • Up to episode 4 of Pluto on Netflix now and it’s really the best anime series of the year for me. Just on those late 90s cybernoir SF mystery vibes. This is what the Ghost in the Shell Standalone Complex reboots should have been like.
    • Also up to episode 4 of Blue Eye Samurai and I’ll admit it’s gotten better. More complexity, somewhat interesting stakes, but the CG anime look with fake low-fps stuttering is getting a little annoying. If I had a modern TV I might actually turn on motion smoothing just to make it a more authentic experience.
    • I tried real hard to avoid buying a 4K HDR TV during the Black Friday sales and succeeded. Gotta save up funds for the dark days ahead.
    • Speaking of premonitions, we saw episode 2 of Lessons in Chemistry on Apple TV+ (mild spoiler alert) and let me tell you, my cinematic Spidey sense tingled and I called the event that happens at the end of the episode minutes before it happened. I’m usually quite bad at anticipating TV twists, but something about the atmosphere and pacing and shots just told me what was coming.
    • We also saw the first two episodes of Monarch: Legacy of Monsters on Apple TV+ and were left impressed. It’s the new series involving Godzilla and other monsters that either belong to Toho or Warner Bros now? Really, the monster custody is unclear to me. But halfway through, as new characters were being introduced in flashbacks, Kim assumed an Asian woman was the mother of a younger Asian woman we’d already seen. And I said, “maybe it’s just an unrelated Asian woman”, to which she laughed, “there are never unrelated Asians”. Which I took to mean in American shows, not the real world, and sadly she’s right.
    • Many people have been raving about Andre 3000’s new instrumental album with flutes, New Blue Sun, and I’ve tried to get into it, I have. But it’s literally put me to sleep a couple of times, so I’m assuming it’s just not for me.

    (This week’s Featured Image is a Dall•E representation of a Chinese Van Morrison impersonator performing in a Muji store.)

  • Week 46.23

    Week 46.23

    1,070 words

    Album of the week: Daft Punk released a “drumless” edition of Random Access Memories and the simple act of removing elements adds an unexpected amount of value. The album strikes a delicate balance between novelty and nostalgia. By removing the drum tracks, it reveals intricate instrumental interplays once masked by robust beats, offering new perspective on familiar melodies. Within minutes, you’ll be surprised at how different this feels. I don’t know how many other albums have been rereleased like this, but it’s a great idea — one made less cynical by the streaming model, as Michael observed in a chat. In the old days, this would just look like trying to sell you a CD you already bought.

    Speaking of cynical purchases avoided, I saw and held the Leica Sofort 2 in person this weekend while attending a talk and exhibition at their annual Celebration of Photography event. The glossy front plastic was not as fingerprint prone as I’d feared, and overall build quality felt a touch better than on the Fujifilm Instax mini Evo: the rocker button on the back panel had more click resistance, the “film advance” lever that prints photos was sturdier and more satisfying to activate, and the flimsy USB port cover on the bottom was slightly firmer and seemed to stay in place. For me, those were the top 3 basic problems that needed to be addressed. The software menus were simply reskinned and not redesigned, as expected. All in all, Leica did the minimum they had to do to make the Fujifilm product a little more premium, but without improvements to image quality, it’s still a very odd product to bear a red dot. I did not feel the urge to replace my mini Evo on the spot.

    Shot on iPhone, edited with looks by ✨PixelGenius

    With Leica’s latest attempt at opening my wallet rejected, my week was free to absorb excesses of a different kind when I met up with Jianjia for a farewell lunch. She decided we would eat Mala at some place called YGF. It turns out that she schedules every meet-up she can there, because she’s addicted to their high sodium spice blend. When I pointed out how salty it was (after she had drunk all her soup, and for the record I couldn’t finish my massive bowl), she was like “huh, maybe that’s why I like it so much. I never had much salt in my food growing up”.

    We are all the products of our childhoods, each messed up in our own special ways, which is something I was discussing with a colleague in a work-related conversation one day when I thought, “ooh, I should make a GPT therapist!” Which I called Doctor Talkabout, and tried to bias it towards exploring barriers to happiness that originated in childhood. On the whole, the unlicensed doctor is now quite good at discussing all manner of problems, and I hope it gives better perspectives than vanilla ChatGPT. And just in case psychology and psychoanalysis are a little too… “real” for you? I also made a GPT therapist based on astrology, inspired by Co—Star. I honestly get a kick out of both, and discussing my problems with them has been more effective at managing my feelings than just going in circles on my own.

    The number of GPTs I’ve made this past week is now in the double digits (including one for work and a private one for editing text), and so I’ve had to make a category page to see them all on this site. Please check them out.

    And yes, some shit is afoot at OpenAI, after CEO Sam Altman was ousted early Saturday morning. Too early to say why, but ChatGPT has noticeably struggled to perform quickly of late, and they’ve both turned off new signups for ChatGPT Plus AND reduced the rate for paying members from 50 to 40 messages every three hours. I have a feeling they might renege on their commitment to open a GPT App Store and share revenue with creators. Time will tell. I wasn’t going to quit my day job for this anyway. And as of Sunday afternoon, he’s supposedly been asked to come back and the board of directors will resign? Pure insanity.

    I watched the first episode of Netflix’s acclaimed Blue Eye Samurai Western anime series, and it felt like something an AI wrote. I don’t get the rave reviews just yet; two people described it to me using Kill Bill as a reference point, and you’ll see why in the super derivative first episode. It even uses the same Tomoyasu Hotei song, Battle Without Honor or Humanity, in a cliche sword-forging and training montage sequence. I mean, Kill Bill itself was a pastiche of samurai movie tropes, but this warms them over without any shame. It also has a dash of Afro Samurai to it, however both of these are examples of how to do homage without feeling like copies. Netflix shows are like cloud kitchen-brand versions of fast food items that were inspired by restaurant dishes.

    Somehow the show has some talent signed up to it: George Takei, Ming Na-Wen, and Kenneth Branagh provide voices. Its writer and co-creator, Michael Green, was involved in Blade Runner 2049 (but also Branagh’s trilogy of Hercule Poirot films which I do not love). But I’ll give it a second chance anyway; there may be other themes at play here beyond the Othered protagonist seeking revenge. But having seen this, I feel like I have a pretty good idea of what AI-generated mass entertainment would look like, and I’m not down for it anymore. I’d like for AGI to come and take away all the other jobs in the world, leaving us humans free to come up with new and more creative ways to show sword fights.

    So imagine my surprise when I started up Pluto (also on Netflix) after two episodes of Blue Eye Samurai, and found it the total opposite in terms of quality. You don’t know where the story is going even if some ideas, like androids that grapple with unexplained dreams from a past life, are familiar and were explored before in other works. It takes its time with characterizations, and aims for a timeless beauty that goes beyond slow-motion action scenes. Polygon has a nice piece about it, but don’t read anything before you’ve seen the first episode, just trust me on that.

  • Co—Sign

    413 words

    Co—Sign: An interactive astrologer and coach for personalized horoscopes and star-guided advice.

    Features:

    • Calculates your star signs when given birth date, time, and location.
    • A talking horoscope you can engage with — ask questions, articulate fears, deflect responsibility!
    • Get general advice with an astrological twist.
    • Type /help any time for an overview of how it works.

    I was never one for horoscopes until I found the Co—Star app in 2019. It’s not that I suddenly became a believer, but I liked how it gave me random prompts and lenses to consider life’s events through, like spinning a roulette wheel to determine what attitude you should meet the day with. And why not? Letting the stars set you secret objectives can be both a fun challenge and a reminder not to take anything too seriously.

    But the “problem” with horoscopes (excluding those delivered by a fortune teller) that Co—Star doesn’t solve is how their provocations can be quite cryptic and vague. Sometimes you just want to ask a follow-up question!

    Which brings us to the magic statement: “Now with AI”. I made Co—Sign to be a GPT astrologer and life coach you can have a conversation with, and not just ask for a more detailed reading, but talk through problems or situations you’re facing. Instead of generic advice, it’ll give you options that take your astrological traits and temperament into account.

    This was probably the hardest GPT to make yet. I must have spent hours trying to get it to reliably calculate your star signs based on birth date, time, and location. It’ll figure out your natal chart from those inputs, i.e. where all the planets were above you in that moment, and use those to guide its readings. There are astrology calculators online for that, but I wanted Co—Sign to be able to figure it out for itself.

    To begin, you can give it those data points and get an initial interpretation of who you are, or just say hi and let it guide you. From there, ask for a daily outlook, or weekly, or whatever. Ask it for advice, ask it who you’re compatible with, any of the standard things. I recommend keeping one chat open to come back and reengage with it, so you don’t have to calculate your star signs over each time (it can take awhile.)

    Here’s an example of me saying I’m afraid I’d impulse buy a Leica Sofort 2 while attending an exhibition this weekend:

  • Doctor Talkabout

    305 words

    Doctor Talkabout: A thoughtful “psychologist” exploring happiness and paths to fulfillment.

    I find talking about problems a great way to start feeling better, even better if the listener has some insightful perspectives or solutions, even if it’s just a reframing of what you said. While talking to someone yesterday about actual therapists and how long it takes to bring them up to speed on your situation and get to know you, I wondered if an AI chatbot could accelerate the process and get to insights and solutions faster.

    So, I made Doctor Talkabout. It’s instructed to ask questions, consider the root causes of your problems/feelings, and apply a range of psychological schools of thought as you converse. You can start talking to it about a specific situation you’re in, or just say hi and let it get a sense of how happy or fulfilled you are, and figure out how to make improvements from there.

    I tried it out myself for something that I’ve spoken to therapists about, and was impressed by how it was able to succinctly articulate some helpful concepts, in some ways better than the humans did. I think it comes down to how a person thinking on the fly is never going to deliver their thoughts perfectly each time, but an AI (assuming it has the right idea at all) has a much higher chance of consistently phrasing it well.

    (I must stress that this is an AI chatbot, and you shouldn’t rely on it to solve real problems; see a trained professional if you need help. It’s partly for entertainment, partly a tool for thinking through your thoughts and situation productively when alone. If you have any reason to doubt OpenAI’s commitment to data privacy, then please do not use this to talk about personal matters or your mental health.)

  • DemystiFi GPT

    319 words

    Explaining money, economics, and the financial world in simple terms. No question is too dumb!

    I must stress that DemystiFi is not a substitute for professional financial advice or your own research. But I started on my personal finance journey quite late by all accounts, only saving and not investing for the first decade of my working life, and missing out on much of the 2010s bull market. It was a different time: no robo-advisors, no apps for buying stocks, and not a whole lot of financial education in the system.

    One of the great things about ChatGPT and generative AI models is that you can learn by having a conversation, with a lot more flexibility than just searching and reading online articles that may or may not answer your questions directly. But without explicit intervention, a lot of the info you receive will still come phrased in the secret language of finance, which isn’t especially useful for people who know so little about money they’ve resorted to asking a chatbot for help!

    So I made DemystiFi to explain things in simple terms, using analogies and plain language. When it uses a financial term, it’ll stop to explain it. If you act like you know a little bit, it’ll gauge your level and ramp up to match you.

    You can ask it about current events (like the announcement of a new inflation figure) and it’ll search the web to find out what happened and explain the implications to you. You can also ask it to help with matters of personal finance, like calculating how much you should save each month in order to retire at 40. It’ll work out some formulas, generate code to calculate it, and give you the results.

    It’s basically the finance friend I wish I had when I was starting out, and still need many times a month these days. I hope it helps you too.

  • Name Guardian GPT

    140 words

    Okay this one’s a bit childish but useful! Or at least well intentioned. You know how some names just lend themselves to being made fun of, and you’re like… “what were the parents thinking?” Or maybe your name is just fine, but you’re about to marry someone, or your parent is remarrying, and your last name might change into something problematic.

    Name Guardian is here to solve this very niche problem. It will check your name for several “vulnerabilities”, namely does it sound like something rude? Does it have double meanings? Will your initials spell something unintended? Might different forms or contractions of your name have some cultural significance somewhere?

    It even kinda works with Mandarin Chinese names, but it admittedly can’t do anything about dialect names. YMMV but it worked on all the English names I tested it on.