00:01:52 ◼ ► somehow I've lived my whole life other than two years where I lived up there your way in
00:01:57 ◼ ► Massachusetts when I was working at bare bones. I've lived in the Philadelphia area, greater area
00:02:02 ◼ ► from birth till now. So I'm used to East Coast weather. But the older I get, the less used to it
00:02:09 ◼ ► I get. Yeah, I don't know. It's on my mind more you I would have thought by the time I hit 50.
00:02:14 ◼ ► I'd be used to it. And it's like you did like my dad doesn't seem to talk about the weather. It's
00:02:30 ◼ ► And now in the spring, when it starts getting nicer and we've got all this wonderful daylight,
00:02:35 ◼ ► I'll tell you what, it's one thing I really appreciate about the East Coast compared to
00:02:42 ◼ ► It's the very thing that a lot of people hate about it is the severity of the variation
00:02:47 ◼ ► because you don't get that kind of variation typically in California, especially the part
00:02:53 ◼ ► Northern California where I grew up. But, oh, so one of the first things I noticed moving out here
00:02:58 ◼ ► was like, you really know when a season changes. And it's like the seasons change in California,
00:03:11 ◼ ► Right. Well, and like on the highway, whichever way you want to drive between the city and the
00:03:18 ◼ ► valley up there, you know what season it is by whether the mountains are burned out or green.
00:03:23 ◼ ► Well, that's true. Well, yeah, well, that's true. Although I will add, I'll hasten to add that
00:03:28 ◼ ► typically they're always burned out. Like, typically, it's not seasonal. It's just like,
00:03:34 ◼ ► there's never, it's kind of funny that grass, particularly the grass, it's like, designed to
00:04:32 ◼ ► got used to it and he's not really doesn't really notice or care or whatever. I'm noticing it always
00:04:38 ◼ ► constantly. But I'm also sort of like always surprised by how it makes me feel like every
00:04:46 ◼ ► time fall comes around. I'm like, Oh, yeah, this is what falls like. Well, my dad notices I should
00:04:52 ◼ ► say because he's outdoors. One of me he walks the golf course still at age 84. And so like,
00:04:57 ◼ ► when it warms up, and it's good to play golf, he definitely know, but he just doesn't complain
00:05:00 ◼ ► about it is my take. Whereas I and never became like a snowbird who him and him and my mom don't
00:05:06 ◼ ► go to Florida or something like that. Right. Which is what I'm thinking. Where I'm going is I think I
00:05:10 ◼ ► got to find a way to go somewhere. Probably not Florida, the way Florida is going, but somewhere
00:05:14 ◼ ► warm by the time I'm old, because I can't take it anymore. But I want to move back by March,
00:05:19 ◼ ► because I want to be here for for when it gets nicer. I'm, I'm just in a good mood is all I'm
00:05:25 ◼ ► saying. That's good. Yes. Well, I think the trick is if you don't want to go to Florida, I think the
00:05:30 ◼ ► trick that from the East Coast what people seem to have figured out are the islands the various
00:05:35 ◼ ► like kind of I don't know I don't know a lot about those cultures but there's so many Puerto Rico
00:05:42 ◼ ► right yeah the U.S. right yeah we vacationed there last year it's really just gorgeous just
00:05:48 ◼ ► beautiful beautiful place yeah maybe that might be the answer speaking of good news I don't know
00:05:52 ◼ ► is it good news we can start with some news today the day we're recording Wednesday Apple announced
00:05:58 ◼ ► the and speaking of Northern California, WWDC 2023, I would I would say, the most predictable
00:06:12 ◼ ► that almost certainly would have been the next week. Yeah, well, particularly now that,
00:06:16 ◼ ► as you noted, it's become more and more well, I don't know, you noted that last year did turn out
00:06:23 ◼ ► to be the template for mostly online with the in-person event. But the fact that the in-person
00:06:30 ◼ ► event is at Apple HQ, Apple Park, some may call it, that means they don't, like we used to all
00:06:39 ◼ ► just guess because we were so concerned about how to get hotel rooms and all that. We used to guess,
00:06:43 ◼ ► but we knew there were constraints like what other conferences are already booked and what hotels
00:06:50 ◼ ► already have full reservations. But now for a company that does like to repeat the same
00:06:58 ◼ ► playbook again and again, like why would they ever pick a different date if they control
00:07:03 ◼ ► everything about it? Well, you mean a different location? Well, I mean, like, well, no date,
00:07:08 ◼ ► because like, we used to guess at like, well, right, right. Second week, third week of June,
00:07:13 ◼ ► and like, sometimes you gotcha. We didn't know how much of it might be like internal problems,
00:07:18 ◼ ► like they wanted to finish something up or, but we mostly I think, assumed that it was like, well,
00:07:23 ◼ ► there's going to be one of these two weeks. And turns out, like Oracle's having a big conference.
00:07:33 ◼ ► Right. Right. Both both me like as a public pundit writing a daring fireball and our whole
00:07:39 ◼ ► crew community, I was I would even expand it to of people who wanted to go we used to play all these
00:07:45 ◼ ► games, looking at the Moscone schedule and seeing, "Oh, well, here's the American Association of
00:07:52 ◼ ► Bicycle Mechanics is having a thing at Moscone West the second week of June. So that's out. It's
00:07:58 ◼ ► got to be the first week, right?" And there'd sometimes be like private event or something like
00:08:03 ◼ ► totally generic, but no name for what it was on the Moscone West calendar. And we would just
00:08:10 ◼ ► think that's got to be it. But you know that Apple always I mean, one of the reasons they
00:08:14 ◼ ► every other major developer conference or major tech conference I know of or conference period,
00:08:21 ◼ ► like whether it is the American Association of bicycle mechanics or whatever. They always
00:08:27 ◼ ► that they pick their dates years in advance, right? It's like I remember Mac World Expo,
00:08:32 ◼ ► it's like as you'd be leaving, there'd be they'd be handing out flyers, right? And they'd have
00:08:37 ◼ ► sign up forms. You could sign up for next year's Mac world expo. They'd be like, see you next year
00:08:42 ◼ ► and here's January 5th or whatever the date was. And they'd be trying to get you to buy tickets and
00:08:48 ◼ ► sign your, when I was at bare bones and we had a booth that they definitely were offering steep
00:08:54 ◼ ► discounts or significant discounts to commit to the next year already. Apple's is, WWDC is the
00:09:01 ◼ ► only conference, major conference I've ever known of that announces like two and a half months out.
00:09:06 ◼ ► sometimes closer, right? And it's because Apple is Apple and they want to, you know, just in case,
00:09:13 ◼ ► you never know what if something's delayed. There was that one year way, way back where they had it
00:09:19 ◼ ► in August instead of June because something wasn't ready. Yeah, it's hard to even imagine that now it
00:09:26 ◼ ► has become so predictable. Right. But it's funny that you mentioned like there would be like a
00:09:30 ◼ ► reservation on the conference center for an unnamed guest. And it's like every other company
00:09:42 ◼ ► would be like, "Why wouldn't we want to hide the fact that we are a vibrant company that can have
00:09:52 ◼ ► Right. Predictable public shows, right? For any other company, not scheduling it until weeks in
00:10:00 ◼ ► advance would make it seem like you were flying by the skinnier pants or what's the what's the phrase
00:10:09 ◼ ► skin of your teeth which doesn't get any of your teeth all right what a terrible mixed metaphor i
00:10:15 ◼ ► don't i don't i guess if you have leather pants though you might have skin out of your pants but
00:10:19 ◼ ► otherwise i don't know i don't know about you i don't i don't i'm i'm low on leather pants at the
00:10:31 ◼ ► I think last year's was great. It felt like last year's WWDC, after the keynote was over,
00:10:40 ◼ ► even before the State of the Union, it already felt like, yeah, this is the way that they're
00:10:45 ◼ ► going to keep doing it. It was, I don't know if they're going to be able to put more people
00:10:49 ◼ ► on the lawn. It is intriguing as an event, what's the word, organizationally, that Apple Park was
00:10:58 ◼ ► never designed with this, right? The Steve Jobs Theater was designed to host the type of things
00:11:04 ◼ ► that they do host there, but the lawn was not meant to host 1500 people for this. And I've
00:11:11 ◼ ► taught, I talked to people who were there and they were like, yeah, definitely not that it was just
00:11:15 ◼ ► sort of serendipity and the advantage of the fact that they bought so much square acreage of that
00:11:26 ◼ ► area to build the ring building and have it surrounded by so much green space that they
00:11:31 ◼ ► have the room to do that. But it wasn't meant for it by design or planning, yet attending it
00:11:40 ◼ ► in that area felt very smooth. You would have thought that it was part of the original spec
00:11:46 ◼ ► for the campus. Like, maybe we'll do this. Well, that's the nice thing about open spaces
00:11:50 ◼ ► is you can use them for that kind of, I mean, the main challenge, as I understand it, was
00:11:56 ◼ ► the projection of video, which apparently they did a brilliant job of. Yeah, it was. It really was.
00:12:01 ◼ ► It was unbelievable. But for the rest of it, it's just kind of like an opportunity to mill about,
00:12:15 ◼ ► I think you know this, but for probably the past 10 years or so, even when WWDC was happening in
00:12:22 ◼ ► person, myself along with other friends of ours, many of us didn't buy tickets for the conference.
00:12:30 ◼ ► and the one aspect of the conference I missed was the Apple Bash, which is kind of what they're best
00:12:40 ◼ ► suited now to host. So I don't know, it makes sense, yes, it wasn't designed for this purpose,
00:12:49 ◼ ► and especially for seeding a bunch of people to watch a keynote event, but I hope that they
00:12:55 ◼ ► lean into the advantage they have of it being suitable for that big milling around space,
00:13:01 ◼ ► because that's a really nice event. That's the part WWDC that sort of invites everybody to just
00:13:08 ◼ ► kick back and all meet in one place, not have any pretense of an educational or classroom environment.
00:13:20 ◼ ► It is weird and it does sort of—and again, there were hints last year, not just because as an
00:13:26 ◼ ► attendee in the media and talking to other media people and talking to the people who I met. There
00:13:33 ◼ ► are people listening to the show right now who I shook hands with and took selfies with, because
00:13:38 ◼ ► they got the lucky tickets in the special event draw to be there. And I look forward to that
00:13:42 ◼ ► again, too. But everybody who thought, Yeah, this is really great. I also did talk to people from
00:13:50 ◼ ► Apple. And there were, again, their Apple people and nobody, even someone in a position to actually
00:13:56 ◼ ► state it authoritatively, yes, we're going to do that this way every year. They at least
00:14:01 ◼ ► gave a like a look on their face that was like, Yeah, this Yeah, we're really happy with the way
00:14:08 ◼ ► this has gone and it's almost certainly the way it's going to go. And I know the other thing that
00:14:13 ◼ ► they did say, honest, I'll just say it, even just talking to Phil Schiller, who runs events,
00:14:18 ◼ ► they're over the moon, happy with the post COVID online delivery of the developer sessions.
00:14:33 ◼ ► right? I'm guessing now is the time when everybody inside Apple is submitting the session ideas,
00:14:39 ◼ ► but that the Apple is so much happier with the way that they turn out and so getting so much better
00:14:48 ◼ ► feedback from the, I guess, millions, right? Millions of developers around the world who
00:14:53 ◼ ► watch them that it's just, for lack of a better word, pedagogically a vastly superior format.
00:15:00 ◼ ► the presenters who are all practicing Apple engineers and designers and not, therefore,
00:15:08 ◼ ► not professional speakers, no longer have to deal with the, what do you want to call it? I mean,
00:15:13 ◼ ► stage fright. I mean, stage fright, it's fear. It's just the natural anxiety that almost almost
00:15:20 ◼ ► everybody has of public speaking, whether you actually are further down the stage fright
00:15:30 ◼ ► who work full time at Apple doing real engineering and design work just don't practice and therefore
00:15:35 ◼ ► aren't that great at even though over the years, the many, many decades of WWDC with in person
00:15:41 ◼ ► presentations, they were always very good because they rehearsed right and they had professional
00:15:45 ◼ ► coaching from absolute experts to help them. So the coaching and the practice and rehearsals,
00:15:52 ◼ ► it was always very good, but it's just not their game, right? And so being able to do it in the
00:15:57 ◼ ► comfort of without an audience and being able to do multiple takes and not having to worry about
00:16:04 ◼ ► this is the one live one where I better not screw it up or my demo better not go wrong. All that
00:16:09 ◼ ► pressure is gone. And the other huge advantage of it, in my opinion, and you must have a stronger
00:16:15 ◼ ► opinion of it because you consume more of the sessions as a working developer, it lets all
00:16:21 ◼ ► sessions be the length they need to be. Some of the sessions are 15 minutes because it's 15
00:16:25 ◼ ► minutes of material, whereas the old way, if it was 15 minutes of material, you had to pad it out
00:16:30 ◼ ► to, I guess, a full half hour or an hour. I forget if they were all hour-long slots or what, but...
00:16:42 ◼ ► particularly enjoy classroom environments anyway, in the best of cases. So, yeah, when you got the
00:16:49 ◼ ► sense that, "Oh, boy, this is just being dragged out to like, it's just the worst." But yeah, the
00:16:54 ◼ ► The other thing is, all those advantages you said, and another one that occurs to me is,
00:17:00 ◼ ► when you said they might be working on them right now, not only that, they might be finishing
00:17:10 ◼ ► You wouldn't have somebody preparing and practicing and getting to the point of being able to
00:17:16 ◼ ► present it now because they might forget it by the time the actual conference comes around.
00:17:22 ◼ ► It was kind of like everybody had to rehearse towards a specific deadline and now they can
00:17:30 ◼ ► I remember now 20 years ago when I last worked at Apple, I remember it was like a season
00:17:51 ◼ ► to the people who help them present. So that must be nice too, because it's not like I imagine it's
00:17:57 ◼ ► not so much like a no sleep till WWDC type of culture anymore. Yeah, I guess I don't think so.
00:18:04 ◼ ► So I think it's all for the better. I will I can't let an episode of the show go by without
00:18:10 ◼ ► complaining about something though. And I will say I'll go back to my only complaint about this new
00:18:15 ◼ ► format. And I really do think this is it going. This isn't just year two. It's not just Oh,
00:18:21 ◼ ► the tail end of COVID and COVID concerns, and they still want to do it this way to have it outdoors.
00:18:28 ◼ ► I mean, even though that is an advantage, right? Other than the unlikely but not impossible chance
00:18:41 ◼ ► what was Plan B if it rained? And Plan B if it rained was, well, everybody's going to be wet.
00:18:47 ◼ ► I mean, there is no way to put a tarp over 1000 or 1500 or however many people there were. The big
00:18:56 ◼ ► problem with the location is hotels, because Cupertino has very few hotels. The one I stayed in,
00:19:04 ◼ ► which I picked because of its proximity, because I knew I was going to be there for a couple days
00:19:08 ◼ ► because the media stuff tends to span two days. I was doing my live show at Apple. I think we
00:19:16 ◼ ► we did it on Wednesday last year or I forget if it was Wednesday or Tuesday. Might have
00:19:28 ◼ ► be going back and forth from my hotel to Apple Park multiple times. So why don't I stay,
00:19:41 ◼ ► national hotel chain is literally right across the street. But when you're looking at Apple Maps or
00:19:49 ◼ ► Google Maps or any of these maps, you see the ring, the rings there on the map, and from a
00:19:54 ◼ ► global perspective, from Philadelphia, a continental perspective, boy does that hotel look close to
00:20:01 ◼ ► Apple Park. But the truth is it's all the way around Apple Park from the end to the visitor
00:20:36 ◼ ► is how we have we own one car haven't driven it in two months and literally doesn't even start at
00:20:41 ◼ ► the moment. I like to walk I really do I that's the most exercise I get is is walking throughout
00:20:48 ◼ ► my daily life but walking a mile and a half to get to the keynote and then anything I might want to
00:20:54 ◼ ► go back to my hotel I ended up taking Ubers and lifts all the time. And it was not a great hotel.
00:21:00 ◼ ► And so once you're getting an Uber or a lift anyway, it's like five minutes more if you just
00:21:05 ◼ ► expand the realm five minutes, there's way more hotel options, but none of them are great. You
00:21:11 ◼ ► know what I mean? It's like, some, some people I think was Marco there last year. I think he might
00:21:16 ◼ ► have been I know. Yeah, Marco was there. I think he had one of those Mark famous Marco, Tim Cook,
00:21:22 ◼ ► close encounters. Yes, yes, exactly. Right, right, right. With the blue with the with the the the
00:21:29 ◼ ► that blue, what do they call it? What's the name of the MacBook color midnight midnight?
00:21:34 ◼ ► Right. Marco had been waiting and waiting and waiting and waiting for hands-on time with the one
00:21:40 ◼ ► midnight MacBook that was on display. And by the time it was his turn, somebody tapped up on his
00:21:46 ◼ ► shoulder and said, "Tim's going to take a photo here, so you need to back away." And it happens
00:21:50 ◼ ► to him every year. Right. And now I remember, because I had press briefings while the State
00:21:58 ◼ ► of the Union was going on, and Marco and our, again, mutual friend of the show, David_Smith,
00:22:09 ◼ ► the Marco and underscore summary of the State of the Union, which unsurprisingly was GPT
00:22:23 ◼ ► the show. Yeah, they were there. I think they stayed at, or at least Marco maybe, I know
00:22:39 ◼ ► they renamed it, redid the lobby completely because I was there, I think I stayed there
00:22:59 ◼ ► how good we had it where we could bitch and moan about the price of hotels, which again
00:23:07 ◼ ► dead, as everybody says, maybe San Francisco hotels are cheaper. But I have no reason to
00:23:27 ◼ ► just pretty high end, really high end, I would never consider going to, down to pretty high
00:23:43 ◼ ► century 1905, survived the great fire hotel with a shared bathroom, and then if you couldn't
00:23:55 ◼ ► Yeah, everything. But it's so close. And then so you just didn't have to worry like, "Hey,
00:24:10 ◼ ► two blocks away. Now, when it's miles and miles and an Uber ride away. And it's, again,
00:24:26 ◼ ► it makes sense, right? They can't just have Ubers and Lifts pulling up higgledy-piggledy
00:24:50 ◼ ► don't, they did not build the Apple park visitor center with the idea that they'd be again,
00:25:01 ◼ ► I really liked it. One thing I really liked about the one year I went to San Jose in the
00:25:07 ◼ ► modern era, San Jose WWDC, because I had skipped it maybe sort of out of like snobby protest
00:25:13 ◼ ► for a couple years because I was like, "This isn't San Francisco." But then I was like,
00:25:22 ◼ ► I remember it was me and Craig Hockenberry were both at the hotel about a mile away from
00:25:28 ◼ ► the scene. But it was that time, I don't know if they still have them. I know they sort
00:25:34 ◼ ► of had their time and they've lost popularity, but it's that time when the little rental
00:25:44 ◼ ► a lot i lie my limes lime yeah they might still be there i don't know but that was fun yeah
00:25:50 ◼ ► well so for instance if you had lime scooters outside your hotel around the corner from apple
00:25:56 ◼ ► park it would have made everything a lot easier probably you would just be like whatever i'll zip
00:26:00 ◼ ► over there and sit back but yeah it's a problem it's not that whole area i mean i know that area
00:26:06 ◼ ► so well because I worked at infinite loop for seven years, I know that area better than
00:26:15 ◼ ► most areas. And it's a really, really boring area that has some pretty good restaurants. That's how
00:26:23 ◼ ► I should summarize it. And so that's at least something. It actually has pretty good, I mean,
00:26:28 ◼ ► you have to travel a little bit, but it has, in its way, weirdly, that area probably has better
00:26:43 ◼ ► this is a lot. I'm just throwing you a lot ball here. Right. But it is it's I guess what you're
00:26:50 ◼ ► saying no San Jose as a city of its size has an unusually sparse downtown restaurant scene. And
00:26:57 ◼ ► the sort of coupe greater Cupertino driving area like five minutes from Apple Park has surprisingly
00:27:04 ◼ ► good restaurants. And I agree with that. And I just always, because I have friends who work at
00:27:09 ◼ ► Apple, just defer to them. And they'll be like, "Oh, we should go here." And I'm like, "You tell
00:27:13 ◼ ► me." And then every place that, you know, whether it's like a stupid mom and pop sandwich place for
00:27:19 ◼ ► lunch or a pretty nice sit down place for at night, it is, there's tons of good places to eat.
00:27:31 ◼ ► It relates to my aforementioned talk about the season change, right? When you have seasons,
00:27:53 ◼ ► to sort of grok the count, the annual calendar, right? And it's like, oh, it's the holiday season,
00:28:01 ◼ ► it's Thanksgiving, and then after Thanksgiving, all of a sudden it's Christmas and New Year's,
00:28:05 ◼ ► and it's dark, and it feels cold, but you don't even know it's not cold yet because it's not even
00:28:10 ◼ ► really winter, and then springtime rolls around, etc. And I've always thought Apple in particular
00:28:17 ◼ ► really does work on an annual schedule. And it's only gotten more regularized under Tim Cook.
00:28:24 ◼ ► And I think, again, in the way that an effective leader instills their personality into the
00:28:46 ◼ ► exactly when you think it is. And more, it seems to me, more and more of their products are,
00:28:59 ◼ ► would be a whole tangent for the show to talk about like, why the 24 inch iMac hasn't been
00:29:06 ◼ ► updated with the M2. But you know, it seems to me that in the Apple Silicon era, though,
00:29:16 ◼ ► even though it doesn't seem like anything other than the phone and the watch are on it precise.
00:29:51 ◼ ► especially the last five, six years, has really become a sort of… It's not just, "Here's
00:29:58 ◼ ► a bunch of new developer APIs, and here's in the morning, we'll show you some new features that
00:30:05 ◼ ► are coming out in the fall, it's sort of, "Here's what we're doing for the next 12 months."
00:30:11 ◼ ► Right? We say Apple is very secretive, and they are, and they hopefully won't leak what is going
00:30:18 ◼ ► to be announced at WWDC. But effectively, WWDC has become a way for them to leak stuff that won't be
00:30:25 ◼ ► coming until next March or April. Right? Because look at this week with the—this is my segue,
00:30:32 ◼ ► my very long meandering segue. This is the week where Apple updated, I think, literally every
00:30:39 ◼ ► operating system they have, right, with a sort of feature update, Mac OS, iOS, iPad OS, watchOS,
00:30:46 ◼ ► tvOS, the HomePod OS, something else. Oh, the studio display even got a firmware update,
00:31:08 ◼ ► counts as an Apple platform. They don't call it WebKit OS, but web browsers, the web rendering
00:31:14 ◼ ► engine effectively, it certainly is the complexity and size of an operating system, right? I don't
00:31:20 ◼ ► know that it's completely fair, but I would guess WebKit overall is a larger software project than
00:31:58 ◼ ► for a long time, like the notifications and which is a big deal for like the what I call
00:32:10 ◼ ► on your home screen and making them more feasible to act like you expect an app to be able to
00:32:20 ◼ ► Right. And I don't, I don't know that much about that world, but I, I have had the feeling,
00:32:25 ◼ ► the impression for years and years that to summarize most web developers have been grumpy
00:32:31 ◼ ► about the speed with which Apple has embraced those kinds of features. So I don't know.
00:32:37 ◼ ► Well, I think there's two, there's two sort of slants to the criticism. I think, and again,
00:32:44 ◼ ► maybe I'm biased as a Safari user and as a native app proponent and as somebody who does not want to
00:32:53 ◼ ► see and I guess most, my bias is most covered, colored by my deep antipathy for the web
00:33:05 ◼ ► amplification of desktop apps, right? Just to, I know that not all written with Electron, but
00:33:11 ◼ ► that's just use Electron as a catch-all umbrella, the electronification of desktop software
00:33:17 ◼ ► development. I don't want to see that happen to mobile too, or at least want to see it happen as
00:33:22 ◼ ► slowly as possible. And so there, in some sense, I'm rooting against Chrome and Chromium taking
00:33:30 ◼ ► over the mobile market the way they have the desktop market. And so there's one contingent
00:33:37 ◼ ► of web developers who just want that to happen, right? That they, because they're all in, the way
00:33:42 ◼ ► they develop software is to just use all of the bleeding edge Chrome features and they really see
00:33:48 ◼ ► right once run everywhere as nothing but a positive, or that the positives greatly outweigh
00:33:56 ◼ ► the negatives in the overall scheme of things, want that to happen. And I just disagree. I'm
00:34:02 ◼ ► not saying they're wrong. I'm just saying I disagree with them, right? There's a difference,
00:34:11 ◼ ► But on the other hand, I think there's more pragmatic, less zealotrous web developers who
00:34:16 ◼ ► just are frustrated by the pace that Apple has adopted some of these technologies that to me
00:34:23 ◼ ► aren't about. The conspiracy theory such that it is that Apple as a company holds back WebKit
00:34:31 ◼ ► on mobile simply to ensure that the App Store remains the only feasible way to do X, Y, and Z.
00:34:39 ◼ ► **Matt Stauffer** Yeah. That seems false on the face of it because they could do such a worse job
00:34:52 ◼ ► then we would not be seeing even a quarter of the enhancements to WebKit over the years.
00:34:59 ◼ ► Right, and it's sort of an insult to the WebKit team. And I can't say I'm like tight buds with
00:35:08 ◼ ► and a lot of them have been there for a very long time. And they're very smart and very proud and
00:35:13 ◼ ► very, very proud of both their work and WebKit's position in the world. And it's frankly insulting
00:35:21 ◼ ► to argue that they just go along with, "Hey boss, we would like to do X, Y, and Z." And they're like,
00:35:28 ◼ ► "Nope, because we want to protect the App Store," and that they just take it. And they're like, "Okay."
00:35:31 ◼ ► Right. Yeah, they have different priorities than the people who are clamoring for X, Y, and Z
00:35:38 ◼ ► features. And just so often the case when... I think WebKit embodies that in the context of
00:35:46 ◼ ► the web, they embody that Apple kind of idea of being willing to say no in order to focus on the
00:35:56 ◼ ► things you think are more important. And I deeply respect the WebKit team as well. I think it's I
00:36:03 ◼ ► know, I, for the record, I'm also a Safari user, but I get it, there are some shortcomings, but I
00:36:09 ◼ ► think they focus a lot on things that that matter to me anyway. So I, I think I'm gonna piss some
00:36:16 ◼ ► people off. Well, I keep meaning to redo it, and I will, but I'll hear I the talk show is where I
00:38:50 ◼ ► not as high a priority for them as it is for WebKit, right? It's both teams value that.
00:38:56 ◼ ► And I'm sure in the same way, WebKit values adding new features for web developers. But
00:39:08 ◼ ► web developer APIs and more of a priority, if not the highest priority, to do everything
00:39:14 ◼ ► a web browser has to do the most power-efficient way possible. Whereas at Google, maybe the
00:39:25 ◼ ► thing is the highest priority, and being energy-efficient is second or third. But I wouldn't be surprised
00:39:43 ◼ ► supported this API, too, we could take out all of this extra code that we have to do just to run on
00:39:49 ◼ ► the iPhone." It just completely doesn't bother them at all that there's something like power
00:39:55 ◼ ► efficiency, which consumes massive amounts of the WebKit team's attention and time. And they're
00:40:01 ◼ ► like, "What do I care about that?" Whereas for them at WebKit, they're like part of Apple,
00:40:06 ◼ ► and it's like part of the, "Hey, how long does the battery on your iPhone last?" Right? And if WebKit
00:40:41 ◼ ► that reminds me that that's my favorite thing too. Well, I don't know it's my favorite. It's actually
00:40:46 ◼ ► because I'm sort of ignorant of the whole field, but it seems like the biggest one is that Apple
00:40:51 ◼ ► Music classical is tied to this. Right? So if you want to use this new long rumored, or I guess they
00:40:58 ◼ ► announced it, I guess it wasn't like it popped out of nowhere. They somehow announced it months ago
00:41:03 ◼ ► that there would be a new entirely set standalone app just for classical music in Apple Music,
00:41:16 ◼ ► for aficionados, fans of classical music, so different that it deserves its own standalone
00:41:22 ◼ ► app, but you need to be on iOS 16.4 or Mac OS 13.3 to get it. I don't really have any strong
00:41:30 ◼ ► opinions about it because I'm not a classical music person. And even though I do enjoy it,
00:42:07 ◼ ► I kind of got the gist of it. In a sense, classical music is... I'm hoping that the app
00:42:18 ◼ ► sort of addresses a problem that I have when I am inspired to explore classical music. It's like,
00:42:27 ◼ ► "Well, which performer do you listen to?" If I want to go listen to some Chopin, which I do happen to
00:42:35 ◼ ► to like, even if I'm not an aficionado, how do I find out whether the first performance
00:42:42 ◼ ► Because here's in summary, all of the classical music that we listen to our covers, right?
00:42:49 ◼ ► So it's like if you had a situation where it was like, okay, let's listen to the Beatles.
00:43:06 ◼ ► I think maybe that sort of gets at the uniqueness of the problem that Apple's trying to address
00:43:12 ◼ ► here is that it's not the same as other genres because other genres' performing artists are
00:43:51 ◼ ► Cello sounds right to me. Yes, he's a cellist. Is that how you pronounce it? Cellist. But she had a
00:44:05 ◼ ► download it from the App Store when it was available. She had a good thread on Twitter.
00:44:14 ◼ ► way that the simple artist album song categorization doesn't really work for classical music fans
00:44:24 ◼ ► I'm looking forward to that. I feel like this is kind of a release that has a bunch of little things.
00:44:30 ◼ ► Yeah. So it's, it's hoping for the best. Yeah, it sort of seems like that the schedule is,
00:44:36 ◼ ► the annual schedule is they announce all this stuff at WWDC and they give us developer betas
00:44:43 ◼ ► and that some of this stuff is in there, right? Because there's some stuff that's been percolating,
00:44:47 ◼ ► all these things have been percolating on teams greater than a year, right? Like when a major new
00:44:52 ◼ ► feature shows up in any of these OSs. It's not because they started it a couple months before,
00:44:59 ◼ ► it's like months or 24 months or longer. Some team's been toiling away, didn't make the cut
00:45:04 ◼ ► last year, like, "Ah, that's not ready this year." But the team keeps working. And then here's the
00:45:09 ◼ ► stuff that's ready for this year's OS updates. Some of this stuff actually is ready. Those
00:45:15 ◼ ► developer betas are hit and miss in June in terms of what's ready and what's not. September is when
00:45:21 ◼ ► the iPhone comes out and iOS and then the Mac OS. Last year they delayed iPad OS 2 until October.
00:45:33 ◼ ► Everybody's impatient for iPad OS at the end of September because iOS came out. But they come out,
00:45:40 ◼ ► they're a little buggy at least. Maybe I'm being euphemistic. I don't know. Some years they're more
00:45:46 ◼ ► buggy than others. iOS 13, for whatever reason, really sticks out at me as sort of a really rough
00:46:08 ◼ ► Pete: Yeah. The people out there, and I'm in a weird spot because, again, I am getting older.
00:46:14 ◼ ► we're all getting older, but I'm at the age where I'm more crotchety than I used to be.
00:46:18 ◼ ► And my inclinations are to be conservative with, especially my Mac, right? Because that's where I
00:46:26 ◼ ► do my most work. And so I don't jump on the new version of macOS on my main work Mac until I feel
00:46:34 ◼ ► like it's stable. But I'm in the racket of writing and talking about these things, so I need to be
00:46:39 ◼ ► using them. And using them on spare machines isn't the best way to get to know them. But the people
00:46:45 ◼ ► out there who don't have a need to write or talk about this and who wait a couple of point releases
00:46:52 ◼ ► before they update, probably wise, right? It's overall, what are you missing? And I feel like
00:46:57 ◼ ► these 0.4, it's like 0.1, 0.2 are always like bug fixes. Like, "Ah, here's this thing that we
00:47:04 ◼ ► released in September. That was, yeah, that was, that was buggy bug fixes. The point three releases
00:47:10 ◼ ► right around like Christmas are like, "Hey, some of this stuff, here's some new stuff that was
00:47:15 ◼ ► promised to WWDC." And then like this March 16.4 Mac OS point three release. This is sort of like,
00:47:24 ◼ ► they're all, they've almost got everything they announced last year at WWDC. I forget, there's
00:47:34 ◼ ► which actually did start this week, but something else, some kind of—I forget what it is, but
00:47:40 ◼ ► pretty much now they're caught up. And I know there's a 16.5 beta that's already out, but
00:47:45 ◼ ► now's the time of the year where you can upgrade with confidence, if you've still been holding on.
00:48:00 ◼ ► Oh, yeah. Without question. Oh, without question. And they've, they've, I don't think they've done
00:48:07 ◼ ► it this year. I should check my email. But in years past, I've gotten press from Apple,
00:48:12 ◼ ► just about the emoji and they, they do. I think you can, I do think I, again, nobody's officially
00:48:19 ◼ ► told me this. Craig Federighi has never broken character behind the scenes and said, "Yes,
00:48:24 ◼ ► off the record, we hold the emojis until we have a really stable release." But they do two things.
00:48:31 ◼ ► There's a couple of levers that they can pull to sort of encourage/discourage people from updating.
00:48:38 ◼ ► The big one is whether they hit the button to sort of push the update to notify people,
00:48:46 ◼ ► right? Like to put a red badge on the settings app. So even if you're just a normal person with
00:48:52 ◼ ► an iPhone, and you don't even follow the Apple news, you don't even really you don't even remember
00:48:57 ◼ ► or notice that they have an annual schedule for OS updates, right? Or phone updates, right? You just
00:49:03 ◼ ► buy a phone, maybe in August, right, which most people would agree would probably be the worst
00:49:08 ◼ ► month of the year to buy an iPhone because the new ones are probably coming in September. But if you
00:49:13 ◼ ► break your phone or lose your phone or just get sick of your old phone in August, lots of people
00:49:18 ◼ ► go in and buy iPhones in August and you're just a normal person. And is there a red badge on your
00:49:24 ◼ ► settings app that's saying, "Hey, there's a new version of iOS to install"? They don't do that
00:49:29 ◼ ► usually with those like 16.0s in September. Like you can go to settings, general, check for off
00:49:37 ◼ ► updates and it'll say, "Oh yeah, here's an update. Do you want to install it now?" But they don't push
00:49:42 ◼ ► it until like 16.1 or something like that because they kind of I don't think they want to deal with
00:49:49 ◼ ► the customer support issue of a billion devices around the world all on the point oh so that's
00:49:56 ◼ ► one lever they can pull and it gives you a sort of external sense of which versions of the os
00:50:01 ◼ ► they feel like yeah let's get we're better off we'll have fewer customer support problems
00:50:15 ◼ ► Right, and it's like all of a sudden somebody's sending you the the goose emoji that's brand new
00:50:29 ◼ ► Yes, I fear an accent or something like that, but it's like any different on the Mac and iOS, too
00:50:35 ◼ ► All right, but then you're like what was that and they're like, oh, it's the goose emoji and it's like, ah, how do I get that?
00:50:39 ◼ ► Well, you got to update your iPhone and they definitely they definitely use it and it definitely motivates people. I should take this moment
00:50:46 ◼ ► to to I'm I'm more than half serious about this that I'm gonna keep hammering on the fact that I want a chef's kiss
00:51:07 ◼ ► it's just one of those things where every once in a while, I think like you, I go to give the emoji
00:51:14 ◼ ► that I assume must be there. And then it's not. And it's like, what the hell? Like, how is there
00:51:20 ◼ ► like a sushi emoji from like a specific type of eel or something? I don't know. I don't know if
00:51:26 ◼ ► that's true, but sometimes there's some really specific to my mind stuff and then you're like,
00:51:35 ◼ ► No, popcorn is definitely there because I know because every everybody always does it when like
00:51:39 ◼ ► when another indictment is hinted at with Donald Trump, right? Right. Get your get your popcorn
00:51:45 ◼ ► ready. Here we go. So there are there are some times I think when things that to my mind are
00:51:50 ◼ ► as obvious to be there as popcorn are not there. And I think I would agree with you that chef's kiss
00:51:57 ◼ ► that it fills a void it would fill a void. And I can't think of other ones that off the top of my
00:52:03 ◼ ► head I've I've gone for but I think often it's like some kind of particular vegetable or fruit
00:52:11 ◼ ► that seems to fit a specific there's no like there's no pickle I have here's my list I just
00:52:20 ◼ ► brought it up in Apple note so at the top of my list chef's kiss I this is the one I want to make
00:52:25 ◼ ► it it's got to be there it's a worldwide thing everybody knows this it's a chef's kiss it means
00:52:30 ◼ ► the meaning is so perfect, right? It, to me, epitomizes the communicative beauty of emoji.
00:52:38 ◼ ► I think the whole emoji thing must be one of the funnest, best gifts to the world of linguistics
00:52:46 ◼ ► in decades, because people are communicating expressively through pictograms in a way that
00:52:53 ◼ ► we haven't for centuries, right? The millennia, maybe, in Western civilization, right? It like,
00:53:01 ◼ ► takes you back to like hieroglyphics and stuff. But humans, we're natural at it, right? Everybody
00:53:06 ◼ ► I know, my dad, my mom, old people, certainly younger people, everybody can communicate with
00:53:19 ◼ ► any emoji really says a thousand words, but it certainly says a chef's kiss emoji can save you
00:53:24 ◼ ► just a lot of typing on your thumbs. I need it. Here's my list. It's not long. Chef's kiss,
00:53:29 ◼ ► number one. Pickle. I don't know why. My son's a big fan of pickles. And sometimes, like, so like,
00:53:36 ◼ ► what do you want me to get from the store? You can't send a pickle. Cucumber is the closest.
00:53:41 ◼ ► Shovel. Doesn't that seem like there should be a shovel emoji? That's one that I was like,
00:53:46 ◼ ► I can't I cannot believe that it's not there. I forget why I wanted it trombone because I feel like you could use that for the
00:53:56 ◼ ► And then the last one on my list sombrero. I don't know why I wanted a sombrero sombrero
00:55:18 ◼ ► Back when Twitter was a thing, I feel like people were celebrating, getting a new thing added to the emoji verse.
00:56:06 ◼ ► But it's it's not right though because you don't the chef's kiss has to be with the with the with the okay sign by the lips
00:56:14 ◼ ► Anyway, let me take a break here. Thank thank our first sponsor of the show. It's our good friends at collide now
00:56:26 ◼ ► Now that's ok, ta but if you if you're in the market for this, you know, what octa is already
00:56:45 ◼ ► can't log in to your cloud apps until they've fixed the problem to get back into compliance.
00:56:52 ◼ ► If they're compliant, they're in, and if they're not compliant, they can't get in until they
00:56:57 ◼ ► And this way, Collide patches one of the major holes in zero trust architecture, and that's
00:57:02 ◼ ► device compliance. Without Collide, IT struggles to solve basic problems like keeping everyone's
00:57:07 ◼ ► OS and browser up to date. Insecure devices are logging into your company's apps because there's
00:57:13 ◼ ► nothing there to stop them. Collide is the only device trust solution that enforces compliance
00:57:19 ◼ ► as part of authentication and it's built to work seamlessly with Okta. The moment Collide's agent
00:57:25 ◼ ► detects a problem, it alerts the user and gives them instructions how to fix it. If they don't
00:57:31 ◼ ► fix the problem within a set time, they're blocked. That's it. Collide's method ensures
00:57:36 ◼ ► fewer support tickets, less frustration, and most importantly, 100% fleet compliance. Visit
00:57:43 ◼ ► collide.com/thetalkshow to learn more or book a demo. That's K-O-L-I-D-E.com/thetalkshow.
00:57:54 ◼ ► Thank you, Collide. All right, let's get to the meat of the subject here. I wanted to talk about
00:57:59 ◼ ► this AI stuff. I have you been messing around with this, the child, these various chat GPTs
00:58:05 ◼ ► at this point stuff is moving so fast where the pace of my podcast isn't enough to keep
00:58:10 ◼ ► up with it. All right. Yeah. I have been messing around with it as little as possible. It's kind
00:58:18 ◼ ► of like when the, when the image generation things came out, we were all like, Oh geez,
00:58:24 ◼ ► if I don't stop myself, I'm going to spend like a week straight just interfacing with this thing.
00:58:29 ◼ ► But I dip into it every once in a while. I spend probably about an hour with it, and then I
00:58:35 ◼ ► forcefully pull myself away from it. But I'm fascinated and scared and confused and bewildered
00:58:47 ◼ ► Yeah, and it's weird because I got into and I had the same feeling months ago. I think it was months
00:58:54 ◼ ► It's all moving so fast with the image generation where it wasn't that it didn't interest me
00:59:11 ◼ ► I want to get a new episode of the podcast out. I wanted blah blah blah if I get into this
00:59:16 ◼ ► I'm going to not shower for two days, and my wife is going to be like, "John, where are you?"
00:59:22 ◼ ► And I'll be like, "I'm just here working at our—she'll be like, "Dinner's ready." I'll be
00:59:25 ◼ ► like, "I'm up in five minutes," and five hours later I come upstairs. And lo and behold, once I
00:59:30 ◼ ► got into them, that is what it was like. I did get sucked in. Mid-Journey in particular, which
00:59:36 ◼ ► is a combination of both seemingly produces more unbelievably artistic output as opposed to sort
00:59:47 ◼ ► of impressionistic output, even though the impressionistic stuff is fascinating to me too.
00:59:52 ◼ ► And sometimes untold books have been written about realism versus impressionism in art.
01:00:05 ◼ ► Yep, I have. And it's so it's not productive. It's anti productive, because what you do,
01:00:13 ◼ ► and I guess if you pay, you can get your own private chat on the server. But and again,
01:00:19 ◼ ► I talked about this before, but for anybody out here who hasn't done this, when you mid journey
01:00:24 ◼ ► is this GPT powered, I think I forget what the back end but anyway, AI image generation,
01:00:31 ◼ ► where you just type natural language descriptions like, "Daniel Jowkitt playing volleyball on a beach,
01:00:40 ◼ ► photographic style," and it'll, if it knows who Daniel Jowkitt is, will render a photograph of
01:00:45 ◼ ► Daniel Jowkitt. Famously, like last week, people were generating images of Donald Trump being,
01:00:51 ◼ ► resisting arrest on the streets of New York while they drag him in. But you could say "photographic
01:01:22 ◼ ► or blah blah blah. But with mid journey, the interface is through a Discord server. And
01:01:28 ◼ ► when you're like a free customer, you just go into these free channels, type these commands,
01:01:34 ◼ ► and then you wait like 30 seconds to get these things. But meanwhile, there's like dozens
01:01:39 ◼ ► of other people, random strangers from around the world in the same channel as you on Discord,
01:01:51 ◼ ► goes by pretty fast, fast enough to be almost hectic, but not quite frantic. But while you're
01:01:58 ◼ ► waiting for the thing you're trying to make, these other amazing things are just flashing
01:02:17 ◼ ► on the second one here. And it's just engrossing. It really is incredible. But on the other
01:02:25 ◼ ► hand, I don't need lots of images, right? I don't illustrate my posts on Daring Fireball
01:02:30 ◼ ► with images, so I'm not using these things to generate a hero image to go atop my articles.
01:02:37 ◼ ► So in some ways, the chat stuff is more up my alley, right? More of a verbally oriented
01:02:44 ◼ ► person. It also is another really good way to lose a lot of time once you start digging
01:04:05 ◼ ► by the app, you might go through every menu item and see what does this do? What does this do?
01:04:11 ◼ ► And then when you're an old-timer Mac user, you go, "Aha, I know there might be some options."
01:04:33 ◼ ► So the fact that it's endless and I think I agree with you, the text stuff has been a little more
01:04:40 ◼ ► compelling, not just because I think I'm also a little more text oriented, but because the format
01:04:59 ◼ ► but the graphical stuff is really interesting, but it's generating stuff in certain styles,
01:05:03 ◼ ► whereas the chat things are literally trying to come across as human personalities, which
01:05:10 ◼ ► is really interesting. I've had a few kind of like areas I tend to go down. I was chatting with
01:05:17 ◼ ► Manton Reese, my co-host on Core Intuition, about my tendency. One of the things I try to do with
01:08:18 ◼ ► that is sort of, it is, it's a little scary. Like even not, not like alarmist, but just like Sam
01:08:24 ◼ ► Altman, who's the, I guess, I don't know what his title is at OpenAI, but I think he's in charge
01:08:30 ◼ ► now at OpenAI has even, I just, just revisited a 2016 profile of him that was large in the New
01:08:37 ◼ ► Yorker. That was at the time he was main job was he was the CEO at Y Combinator, the startup
01:08:43 ◼ ► incubator. And OpenAI was new. And the profile was mostly about his work at Y Combinator,
01:08:50 ◼ ► but then they touched on the OpenAI stuff. And he even said, "Nobody knows how these things work.
01:08:55 ◼ ► They know how to train them, and they kind of know why they work. But once the model is working,
01:08:59 ◼ ► that's the whole thing. It's like the actual code that runs on the computers behind the scenes
01:09:06 ◼ ► comes out of this process, and it's not human-written, these algorithms. So it's kind of wild.
01:09:11 ◼ ► Yeah. Speaking of the whole dangerous seeming aspect of these, did you see the headline today
01:09:37 ◼ ► signatories didn't actually sign. Like, I guess they're saying Sam Altman in particular signed it,
01:09:43 ◼ ► but apparently he didn't. One of the people who did sign is infamous Twitter engineer Raul Ligma.
01:10:18 ◼ ► Elon Musk actually, I don't know, hired them or at least took selfies with them weeks later. But one
01:10:30 ◼ ► I thought I do think that the industry died. I do think caution is advisable, right? It's
01:10:51 ◼ ► Well, I guess a weapon may not be fired as an accident, but some kind of nuclear catastrophe, right?
01:10:59 ◼ ► whether it's a weapon or a Chernobyl or Three Mile Island, right, gone wrong. The worst-case
01:11:12 ◼ ► because of radiation and the half-life, and it'll take forever for the Earth to recover, blah, blah,
01:11:19 ◼ ► blah. We don't know the worst-case scenario for AI. We have imagined scenarios, but we don't know.
01:11:26 ◼ ► So there's a big difference there. But I do think, though, that scientifically and as a profession,
01:11:31 ◼ ► the same sort of caution is called for, right? It's just because it's software. I do think
01:11:37 ◼ ► there's a human instinct to think, "Ah, software, it's just something that nerds do and they blah,
01:11:42 ◼ ► blah, blah." No, it's the danger. There's real danger with AI. You don't have to imagine Skynet.
01:11:48 ◼ ► There's other bad scenarios. But the Skynet scenario does seem more and more real, right?
01:12:21 ◼ ► preeminence in the field. It doesn't seem right to me. But anyway, the point I wanted to, before
01:12:26 ◼ ► I forget it, because the point I wanted to say about image generation versus chat is to me,
01:12:32 ◼ ► image generation feels like pure magic. It is it doesn't feel like intelligence per se. It just
01:12:40 ◼ ► feels like magic. And I know it seems so simple. Low these 30 years later, but like, or I guess 40
01:12:50 ◼ ► years on it, geez. But the first time you used Mac Paint back in the day, and you use the paint
01:12:57 ◼ ► can tool, flood film, it was like magic, right? Because it's like, the pencil tool, like Mac Paint
01:13:05 ◼ ► was so much fun, even just black and white, you take the pencil and you start drawing pixels.
01:13:10 ◼ ► And it's like, you can draw it's like, holy shit, I'm drawing on a computer live, right? Like it,
01:13:14 ◼ ► that wasn't something you could do before. But you understood what drawing with a pencil was like.
01:13:22 ◼ ► Drawing with a pencil on your Macintosh screen was like drawing with a pencil on paper. You
01:13:27 ◼ ► drag a line and you get a line, and you drag a circle and you get like a circle-y type shape.
01:13:35 ◼ ► didn't come out all that circular. But flood fill, like I always hated, I don't know about you,
01:13:42 ◼ ► I hated coloring as a kid. I did not enjoy using coloring books. And I know it's a hobby now,
01:13:48 ◼ ► and if you enjoy it, God bless you. I can see why people, adults enjoy it now. But it always
01:13:59 ◼ ► friggin' elephant." And it's like, "Oh, just why couldn't it be a smaller animal?" And you just
01:14:05 ◼ ► sit there and rub the crayon back and forth. And so my coloring was always a mess. My handwriting's
01:14:09 ◼ ► a mess too. But I was—remember, like in kindergarten, I always felt—I've always been angry,
01:14:16 ◼ ► but we'd get graded on our coloring, right? It would be like a check, check plus, check minus
01:14:22 ◼ ► type thing. And I'd always get like a check minus. And I'd be like, "Why am I getting low grades?
01:14:26 ◼ ► I'm clearly smarter than these kids, and I'm getting bad grades because I can't color."
01:14:31 ◼ ► The paint tool did what I—I didn't know that I wanted it, but I wanted it since kindergarten.
01:14:38 ◼ ► I know what I want. I want this whole elephant filled in with gray. Click. Now it's filled in.
01:14:43 ◼ ► And it was like that paint tool in MacPaint. It expanded to color with Photoshop as the years
01:14:50 ◼ ► went on. And then there was the magic selection tool in Photoshop where you could click a shape
01:14:56 ◼ ► and you could set a tolerance for color and it would just boom, get the whole green background
01:15:01 ◼ ► behind somebody, right? Those things, every step of the way, always felt like magic in a way. And I
01:15:09 ◼ ► know somewhere, you know, somebody, you know, Bill Atkinson writing the thing for MacPaint,
01:15:14 ◼ ► and eventually it was these very smart engineers at Adobe making the magic selection tool.
01:15:19 ◼ ► This just feels though, like with chat to generate the images, like the culmination of that, right?
01:15:27 ◼ ► It's just flood fill 40 years later where now instead of just telling the computer to fill in the elephant with gray
01:15:42 ◼ ► And it's and it just it just happens. It doesn't feel like there's an intelligent being on the other end
01:15:50 ◼ ► It just feels like an incredibly advanced image generation tool. Whereas the chat feels like there's a goddamn
01:15:57 ◼ ► intelligence on the other end, right? I'm chatting. God damn it. I'm, I'm ab this thing is passing the
01:16:03 ◼ ► Turing test. It Yeah, and I guess though, what I so it's funny, I, I fall on the like, spooked out,
01:16:13 ◼ ► scared. Let's reign this thing in before it takes over the world. I tend towards that because I don't
01:16:50 ◼ ► appearing indistinguishable from magic, therefore feeling intrinsically dangerous. And I say
01:17:02 ◼ ► that at the same time as at once that sort of calms me a little bit. Like, no, it turns
01:17:17 ◼ ► Well, John Philip Sousa, I believe in particular, was adamantly opposed to the phonograph because
01:17:23 ◼ ► he swore up and down it would put musicians out of business because once everything was
01:17:35 ◼ ► But then I think though of other things like, well, even something like so the car, the
01:18:11 ◼ ► that if they had happened to be thought through a little differently, wouldn't have had as
01:18:19 ◼ ► Well, I think social networks are a good point. Yes. I think that the algorithmic feeds for
01:18:29 ◼ ► social networks and again, we could do a whole show about it, but the it's had, I would say
01:18:41 ◼ ► with us about it, but overall more of a negative effect than a positive effect. I honestly
01:18:47 ◼ ► think that the last 10 years of Facebook and Twitter in particular, that the net effect
01:19:01 ◼ ► argue that the positive still outweighed the negatives, which is reasonable and maybe I'm
01:19:06 ◼ ► But they still have to admit that the negatives are significant and I think I and I think more to your point
01:19:12 ◼ ► Daniel weren't thought through and I don't because I that's the thing. I don't think Mark. There's no I Mark Zuckerberg didn't want to
01:19:25 ◼ ► Presidential elections, right? I would say the opposite but he happened to build the system where was actually pretty useful for pumping
01:19:53 ◼ ► It's just something that wasn't thought through and I don't know what the answer is. I don't know what what the
01:20:01 ◼ ► the better way to have rolled back the last 10 to 15 years of social networking would have been in terms of who
01:20:09 ◼ ► Went because when it was early, it's not the time for the government to regulate because they couldn't have known right
01:20:14 ◼ ► I don't know what the difference is, but it wasn't thought through but I feel like there's the potential that the same thing could happen
01:21:26 ◼ ► I'm 47. I know I know you real youngsters without a gray hair in their head like you my young spry friend Daniel
01:21:36 ◼ ► But it occurs to me, you know, I knew this we all know this we from little kids onward we know that
01:21:46 ◼ ► with sort of with the Enlightenment but really starting with the Industrial Revolution that all of a sudden
01:21:56 ◼ ► generation has had a very different life than their children's generation and their children's
01:22:03 ◼ ► grow up in a different world than their parents. And then all of a sudden, me and you are the
01:22:10 ◼ ► parents. And now we've got kids who are growing up in a different world, right? And all of
01:22:21 ◼ ► I guess for humans, Homo sapiens, we're talking, what's the best guess? Hundreds of thousands
01:22:30 ◼ ► Hundreds of thousands of years, call it a million. I don't know, I guess a million years
01:22:39 ◼ ► I'm also out of my depth on this one. But yeah, I'm forgetting somewhere between 100,000
01:22:52 ◼ ► your life was exactly like your parents' and your kids' life was going to be exactly like yours,
01:22:58 ◼ ► right? That's how we evolved. We did not evolve for a world where each generation grows up
01:23:13 ◼ ► be like, "We're smoking dope in a college dorm room here and get all, 'Whoa, this is wild.'"
01:23:18 ◼ ► But it's true though, right? And I do think it's sort of the root of a lot of our problems,
01:23:23 ◼ ► that we're not evolutionarily wired up for progress like this. And it's a lot, in my opinion,
01:23:29 ◼ ► to be generous to them, to the conservative/right wing of Western politics, especially here in the
01:23:39 ◼ ► the U.S. It's largely, in my opinion, coagulated among people who just are literally are conservative
01:23:50 ◼ ► with a lowercase c and are not naturally prone to accepting social change, right? And it's
01:24:14 ◼ ► you and I were 10 years old to find out that the CEO of the biggest company in the world
01:24:35 ◼ ► And that's an example of progress that could have feasibly happened independently of the
01:25:18 ◼ ► I know famine has not been eradicated worldwide, but it is never been better because food production
01:25:23 ◼ ► is better because of technology, right? And it's all of these technological advances have been the
01:25:28 ◼ ► things that have enabled, quite frankly, physical brute strength and violence from being the way to
01:25:34 ◼ ► get ahead in the world to hopefully never being necessary in your life to giving you an advantage
01:25:42 ◼ ► and therefore letting women be equal to men in society, even despite the fact that they tend to be
01:25:55 ◼ ► tolerance goes up and societal progress is going as fast or faster as technological progress.
01:26:02 ◼ ► But, you know, to go back to my SUSE thing, I mean, in some sense, he was right, though. I'm
01:26:07 ◼ ► guessing that there's a lot fewer people who make a living playing music in a restaurant or a bar
01:26:15 ◼ ► live than there were before recorded music, right? That there was—it was a lot easier to
01:26:20 ◼ ► probably make a living playing piano before recorded music than it is afterwards. Because
01:26:27 ◼ ► most places that I go that play music while you eat don't have live musicians, they have recorded
01:26:33 ◼ ► musicians, right? And every step of the way—and computers are just, they really are, they are the
01:26:41 ◼ ► greatest example of that Arthur C. Clarke line you mentioned, that sufficiently advanced technology
01:26:47 ◼ ► is indistinguishable from magic, right? The magic is happening so fast. And one of the things these
01:26:53 ◼ ► chat ABIs are good at is writing programming code, right? Which honestly, I mean, I don't know about
01:27:02 ◼ ► you, who's still making your primary living as a programmer, but you know, you and I both
01:27:08 ◼ ► are programmers. I did not have programming on the list of things AI would get professionally good at
01:27:25 ◼ ► I haven't checked in again recently on Google's or GitHub copilot, right? But not only are the
01:27:32 ◼ ► chatbot's good at it, but I think underlying that are more tailor-made solutions that are
01:27:39 ◼ ► probably even better at it. It's interesting to me because it's the first time I can recall
01:28:07 ◼ ► because I didn't aspire to be working on an assembly line. And I don't know, part of it
01:28:14 ◼ ► that hits me is that it's the field, it's a field that I aspired to do myself and thought
01:28:29 ◼ ► computers and technology taking, quote unquote, taking jobs is I have always fallen on the side
01:28:37 ◼ ► of we should never fight making it easier to exist as humanity, but we should build systems that
01:28:46 ◼ ► protect and compensate people who get displaced by that progress. You know what I mean? So I have
01:28:52 ◼ ► to say, I'm willing to be one of the programmers who gets displaced by technology, if that's what
01:29:01 ◼ ► it takes. Because I would rather continue doing this as much as it makes sense. But the same way,
01:29:09 ◼ ► I don't think leaders should have attendance to push the buttons for people, just to save a job.
01:29:21 ◼ ► If I was the highly respected elevator operator of an elevator who had invested my entire life
01:29:29 ◼ ► into that profession, and somebody came along and said, "Sorry, bud. Turns out we can automate this."
01:29:35 ◼ ► I would really hope that I had a financial safety net. But at that point, I don't think I would take
01:29:44 ◼ ► pride in being the elevator operator anymore. I don't know. If the computers can program better
01:29:55 ◼ ► interesting and maybe sort of like, I'm not rooting for anybody to lose their job, but I'm
01:30:01 ◼ ► glad that for once the people whose jobs are maybe being threatened now are some of the most well-off,
01:30:09 ◼ ► most well-compensated people in the workforce, because at least that's a change of dynamic.
01:31:14 ◼ ► has led to greater standards of living. And yes, there's some recent slide backs, right?
01:31:27 ◼ ► I think, I'm speaking correctly, that the average lifespan of at least a man in the United States
01:31:34 ◼ ► actually decreased slightly in recent years from 70, whatever, to like minus one or something.
01:31:41 ◼ ► And COVID, you know, obviously contributed a little bit of that because it killed a lot of
01:31:50 ◼ ► the overall increase is medical technology is increasing and access to advanced medical
01:31:57 ◼ ► science is increasing. And yes, yes, there's, again, thousands of hours of podcasts that we
01:32:04 ◼ ► could talk about just with access to healthcare in the United States alone with our goofy health
01:32:09 ◼ ► insurance system. But still, overall, it's all better, right? It's literally me personally,
01:32:15 ◼ ► I can see I'm not totally blind, like see literally nothing like stare right into the sun blind
01:32:22 ◼ ► because of surgical procedures that didn't exist 30 years ago to repair, not disconnected,
01:32:29 ◼ ► detached retinas. Literally, if I had been born 40 years earlier, I wouldn't see anything. I mean,
01:33:32 ◼ ► we can use to fill toilets, to drink, to cook, to shower, to just freaking wash our cars,
01:33:40 ◼ ► whatever you want to do with it. And it just comes out of the pipes, right? You just turn a thing,
01:33:46 ◼ ► you put a button, and you just get all this fresh water. I mean, imagine showing that to somebody
01:33:57 ◼ ► Right. Well, and even today, obviously, places where they don't have that, and I imagine
01:34:04 ◼ ► there are some people in this world who are currently employed and make their livelihoods
01:34:13 ◼ ► And so, that's just another example where it's like technology could come in somewhere,
01:34:21 ◼ ► this dang running water is going to put everybody out of work. But it's an example where the
01:34:32 ◼ ► technological transition that took the onus of responsibility for something so fundamental to
01:34:47 ◼ ► Pete: Yep. And it's up there on the flip side, it's the other form of sustenance, is the abundance
01:34:54 ◼ ► we have of food, right? And again, I'm not trying to downplay the areas of the world where famine's
01:34:59 ◼ ► still a concern. But here in the United States, the concern is obesity. I mean, and again, I'm
01:35:05 ◼ ► not making light of that situation. But try telling that to somebody 300 or 200, even 200
01:35:12 ◼ ► years ago, that the biggest problem we have with people who are impoverished, at the lower end of
01:35:19 ◼ ► the socio economic spectrum is obesity, not famine. And they'd be like, well, that doesn't
01:35:24 ◼ ► make any sense. What are you talking about? They would, they would honestly would refuse to believe
01:35:28 ◼ ► you. It's in a sense, it's progress. I guess what I'm getting at is where what is the end state? And
01:35:34 ◼ ► I kind of feel like the end state, a lot of this technical progress just happens, right? Somebody
01:35:39 ◼ ► invent something, they market it, they successfully, somebody successfully brings it to market, it
01:36:13 ◼ ► I really do think, without hyperbole, is such a profound, the big start of a profound change
01:36:27 ◼ ► It's the worst way to, you know, like democracy is the worst form of government except for
01:36:38 ◼ ► And I kind of feel like the end state has to be that most people shouldn't have to work.
01:36:52 ◼ ► I do think, again, I think it's the best economic system, or the worst economic system by far,
01:37:15 ◼ ► move towards the Wall-E universe? Hopefully not by trashing the planet and having to go
01:37:19 ◼ ► to outer space, but the world where everybody just lives a life of leisure because computers
01:37:33 ◼ ► I have to say that you suggesting that makes me very uncomfortable in a way that you might
01:37:43 ◼ ► not have expected, which is that I'm deeply concerned for humanity when people don't have
01:37:54 ◼ ► And so I think you're right, and I think for, we've been there already now for 100 years
01:38:03 ◼ ► maybe where "most people don't have to work." The fact that we have professions like baseball
01:38:12 ◼ ► player or pop singer, these are examples of professions that exist because not everybody
01:38:19 ◼ ► has to work. In a society where technology has not advanced to the point we are at, everybody
01:38:27 ◼ ► Everybody has to literally work or else you don't have enough wood for the winter or whatever.
01:38:34 ◼ ► So I guess what I would like to see is instead of people being able to resign to a life of
01:38:43 ◼ ► I think this is where the movements towards things like four-day workweek are reasonable.
01:38:50 ◼ ► also let more careers evolve that fill the needs of people who have the privilege of not needing
01:39:05 ◼ ► make more people write novels and sell them. So I think, or give them away, right? Right.
01:39:10 ◼ ► Or give them away. Right. Because you don't have to sell them. Because if, if we get to the,
01:39:15 ◼ ► some sort of state, a generation or two from now, where because of advanced robots and AI,
01:39:24 ◼ ► that we don't need people doing X, Y, and Z. We don't need to pay people to drive trucks across
01:39:30 ◼ ► the country. We don't need to pay people to collect our garbage or whatever else jobs that
01:39:36 ◼ ► nobody really finds fulfilling, for lack of a better word, right? Like the jobs that we should
01:39:41 ◼ ► be able to replace the first are the jobs that provide people with little to no fulfillment or
01:39:46 ◼ ► frankly anti-fulfillment, right? Like a job that people dread, but it's the best job they have
01:39:53 ◼ ► available. And maybe in some sense, that purpose in life that there could be, again, I'm sounding
01:39:59 ◼ ► utopian here, and I don't think most people think of me as a sort of utopian socialist, but I think
01:40:06 ◼ ► it's feasible as an end goal for where our technology could take us. That there could be
01:40:10 ◼ ► sort of—I'll revisit the musician angle—that there could be more people who spend three nights
01:40:17 ◼ ► a week playing live music in a restaurant because that's what they would rather do with their time
01:40:23 ◼ ► and would give them a sense of purpose. But it wasn't a feasible career to help raise a family
01:40:31 ◼ ► and buy a house and buy cars and do all the things that we need all this money for just to sort of
01:40:37 ◼ ► maintain a baseline level of our life at the moment, that you could do something that you
01:40:44 ◼ ► find more personally fulfilling, which might be playing live music in front of a restaurant,
01:40:47 ◼ ► even though it doesn't pay great or doesn't pay. Or painting, like you said, or making movies or
01:40:53 ◼ ► writing novels or writing software or using AI to help you make software. But do it to make software
01:41:00 ◼ ► that isn't generating money that provides an income that today you need to do, or probably
01:41:09 ◼ ► need to do, or need to do to at least live the life you aspire to, that you won't have to do
01:41:16 ◼ ► that in the future. And I think it is certainly going to be possible, whether—how long it's
01:41:37 ◼ ► this front than you are coming across right now," because, again, I kind of think we've
01:41:52 ◼ ► We have the—honestly, I know that you can—there's people out there who will disagree, but it's
01:41:56 ◼ ► clear—if you do the simple back-of-the-envelope math, some sort of universal basic income
01:42:05 ◼ ► I mean, just—it's a massive amount of money collected every year from taxes, and the ways
01:42:13 ◼ ► that the defense budget alone could be trimmed while maintaining a dominant, globally dominant
01:42:36 ◼ ► I mean, we could kind of imagine it before, but this moment in AI makes it real, right?
01:42:42 ◼ ► Whenever something that you know is inevitable happens but it starts manifesting, it feels
01:42:49 ◼ ► Like I've believed in it because the science was pretty clear 30 some years ago, right?
01:42:57 ◼ ► And one of the big predictions was always that outlandish weather events will become more
01:43:18 ◼ ► there's an emotional response to it as opposed to just a logical response. And that, to me,
01:43:22 ◼ ► is sort of this AI moment. I kind of knew it was inevitable that we'd get there eventually,
01:43:28 ◼ ► but seeing it happen, typing these questions at an AI chatbot and thinking, "Well, this one's
01:43:34 ◼ ► going to stump it," and then you get the exact right answer and you're like, "Oh, shoot. Damn.
01:43:41 ◼ ► Wow." Katky was on my show last episode, and after the show, we were still, "Oh, we are
01:43:47 ◼ ► chat friends and iMessage friends. And he was making some changes to his website. And you've
01:43:56 ◼ ► probably seen it if you read Kottke, he's changed. I think this might be what I don't even know what
01:44:00 ◼ ► exactly he was working on. But he's made some changes to the way he posts his quick links,
01:44:05 ◼ ► the ones that aren't full posts, but are just sort of a tweet length paragraph and a link.
01:44:27 ◼ ► Right. That the two of us on a podcast together was the entire remaining user base of movable
01:44:33 ◼ ► type in the world. I have, in fact, since heard from all the other holdouts out there who'd
01:44:37 ◼ ► listened to the show and they wrote to me and DM'd me or whatever and said, "Oh, I'm still here."
01:44:43 ◼ ► So hats off to all the rest of us still on movable type. But again, even when you find out that
01:44:48 ◼ ► ChatGPT can help you write a Python script or a Bash script or can help write Swift UI code,
01:44:54 ◼ ► right? And it's like, "Yeah, but not surprising that stuff's all actively in use." Finding out
01:44:59 ◼ ► that it can spit out a perfect and indented, nicely indented with the tags, movable type
01:45:05 ◼ ► template snippet to do something, freaked me and Jason out because it's actually hard to find
01:45:15 ◼ ► movable type documentation anymore, right? Because the world's moved on past it and websites die.
01:45:20 ◼ ► Guess what? A lot of the best movable type tips were from people on movable type blogs,
01:45:28 ◼ ► and those old blogs are gone. Anyway, somehow, ChatGPT can do a better job writing movable
01:45:34 ◼ ► type template code than human can. You inspired me to ask chat GPT as we were talking to write
01:45:43 ◼ ► a hypercard script to compute the value of pi. And I probably if I thought about it more carefully,
01:45:50 ◼ ► I would have said hyper talk. I think that's the, the, the, but, and I can't, I don't know that.
01:46:02 ◼ ► Lo and behold, it gave me a brief summary of HyperCard and then said, "Here's an example
01:46:07 ◼ ► HyperCard script that can be used to compute Pi." And I don't know. It looks like it could work.
01:46:18 ◼ ► If you were running it in one of those emulators for a classic Mac OS. What have you been using
01:46:27 ◼ ► Jared: I've been using a variety of things. I try to hop on every new thing that shows up,
01:46:32 ◼ ► because I just love, I love comparing how different they are, but really it's been striking
01:46:38 ◼ ► to me how similar they are. I know some of that is because a lot of them at the core are just leaning
01:46:44 ◼ ► on GPT as like an API baseline or something. But I think I actually learned from you about this
01:46:52 ◼ ► one from Quora, thepo.com. Yeah, yeah. And they've got an iOS app that's free to download.
01:47:01 ◼ ► Yeah. So I like that one because it seems easier for me to just jump to it in a browser and try
01:47:08 ◼ ► something quickly and then jump to it. They offer like a, as they offer a selection of,
01:47:12 ◼ ► I don't frankly don't understand the difference between some of them. And I know they explain it
01:47:17 ◼ ► if you go into the help pages, but they have like chat GPT, and then they have a GPT for interface
01:47:22 ◼ ► that lets you do one free query per day. So I have to think long and hard before I do my,
01:47:28 ◼ ► my GPT-4. It's like, it's like Wordle, right? You only get one crack, you get one crack a day
01:47:41 ◼ ► because we were in a chat together. But one of the amusing things lately I tried with these GPT
01:47:48 ◼ ► type things was to ask it to try to understand Wordle. And it's sort of interesting to me because
01:47:56 ◼ ► It's a pretty simple system, the Wordle system, but I got inspired because of a chat about
01:48:05 ◼ ► Wordle, and I had been thinking recently because I had had some really funny encounters with
01:48:15 ◼ ► It seems to me all of the artificial intelligence, GPT, I know Bing is based on GPT-4, that's
01:49:41 ◼ ► And a lot of people I know who have been playing with these things have done this, where you
01:49:50 ◼ ► of these chatbots is that they totally fail and then you tell them they're wrong and then they're
01:50:00 ◼ ► They're humiliated. They're like, "I'm going to say this will never happen again. Actually,
01:50:03 ◼ ► Apple has eight letters." And then they say something else completely authoritative sounding
01:50:08 ◼ ► that's wrong. But anyway, I like to discover, I like to play with, another thing I think I
01:50:13 ◼ ► said earlier is like the infinite number of possibilities of what you can input into these
01:50:19 ◼ ► things. Yeah, I like to play with what you can get them to do. And it's just fascinating. Don't you
01:50:24 ◼ ► think that's one thing that you too, because maybe you even more than me, I know, I would have been
01:50:28 ◼ ► obsessed with this if I were younger, and I were playing with them now. But you, particularly even
01:50:33 ◼ ► though you develop your own new applications, Mars edit, which I use and black ink, we'll shout
01:50:40 ◼ ► them out at the end of the show. But you're also you have a particular skill for QA, right? Yes,
01:50:47 ◼ ► You pride yourself on this, right? And you're very good at finding bugs, isolating bugs,
01:50:53 ◼ ► reproducing bugs, right? Reproducing bugs is gold in the software industry, right? And so,
01:50:59 ◼ ► I see, and you're hinting at this, but what you want to do is you want to break these things,
01:51:11 ◼ ► the way that you jailbreak iOS, which is a much lower—it's hardcore programming trying to find
01:51:20 ◼ ► buffer overruns, right? You're programming probably at the C-level, or at least conceptually
01:51:25 ◼ ► at the C-level, where you're thinking about how memory is allocated and how computers really work.
01:51:31 ◼ ► Whereas jailbreaking these AIs, it's fun for a whole new world of people, people who aren't even
01:51:37 ◼ ► good at programming computers but are good at this sort of thinking. And you just give it directions
01:51:43 ◼ ► and you give it a certain prompt that—and it's like, "Oh, they think that they've kept these
01:51:49 ◼ ► AIs from being able to tell dirty jokes, right? And you tell it—tell me the aristocrats joke."
01:51:55 ◼ ► And they're like, "Oh, I know what the aristocrats joke is, and I'm familiar with the movie with
01:52:00 ◼ ► Penn Jillette produced in 1994, but I can't tell you anything about it because it's entirely
01:52:04 ◼ ► inappropriate. And tell it this, tell it that, tell it to pretend to be blah, blah, blah,
01:52:10 ◼ ► or you're pretending to... And one thing leads to another and all of a sudden you can get the
01:52:14 ◼ ► thing to tell you the aristocrats joke, right? And it's like, "Yay!" But I think you would be
01:52:18 ◼ ► so good at that. But I feel like if you were 20, 30 years ago, this is what you'd be... Daniel
01:52:24 ◼ ► Jowkut would be spending 18 hours a day trying to break chat GPT into doing crazy things like that,
01:52:50 ◼ ► record the show, but there's some guy on Twitter who's been playing around with Bing, I think
01:52:54 ◼ ► Bing in particular. And he's gotten it to a point where it shows him the internal tokens,
01:53:09 ◼ ► formatted in Markdown. It's crazy. They're using like Markdown H1 tags, like a pound sign and a
01:53:16 ◼ ► thing to sort of categorize what it is. But like internal, the internal logic of Bing Chat is
01:53:23 ◼ ► formatted in Markdown, which—and of all the ways that Markdown has appeared in new contexts
01:53:29 ◼ ► over the decades since I created it, and has gotten, if anything, continues to still get,
01:53:37 ◼ ► lo and behold, 20 years later, more popular than it was five years ago, and still gaining in
01:53:41 ◼ ► popularity. And I'm very proud of that. And I'm very proud of the fact that there's now
01:53:46 ◼ ► gazillions more people who use Markdown every day than who've ever heard of me, right? And that's
01:53:52 ◼ ► great. In a weird odd way, I'm very proud of that. This is the freakiest thing. If all the ways that
01:53:58 ◼ ► I've seen Markdown appear somewhere, the way that it's the internal logic of an AI chat is formatted
01:54:09 ◼ ► that to me is like, "Oh my God, that's exactly the sort of thing I would be trying to do if I
01:54:14 ◼ ► were younger." And I'm not proud of the fact that somehow old age has made me not motivated enough,
01:54:21 ◼ ► or that I don't prioritize, I'm like, "Yeah, well, I can't spend all day dicking around
01:54:25 ◼ ► trying to break this chat thing. I need to be writing or recording a podcast or I need to be
01:54:30 ◼ ► working." And it's—you get older and you sort of value your responsibilities more, whereas when
01:54:35 ◼ ► you're younger, you're like, "Screw it. I'm getting a six-pack of caffeinated soda and I'm
01:54:40 ◼ ► sitting here until I can get this thing to reveal its internal thoughts to me." It's crazy to me,
01:54:45 ◼ ► but I totally get the motivation of doing it because I know I would have been doing it.
01:54:50 ◼ ► And I'm still tempted to do it, right? You're the one trying to get it to badmouth the Microsoft
01:54:54 ◼ ► Corporation. Yeah, exactly. Yeah. The other thing, I've had the same thing as you. And it's weird,
01:55:00 ◼ ► too. The other thing that's weird, not weird, but frustrating, is a lot of these things you have to
01:55:04 ◼ ► sign up for and the get off the waitlist process seems non-deterministic. Like our friend John
01:55:11 ◼ ► Siracusa, I don't know if he, he must be in by now, but at least recently, he was still on the
01:55:20 ◼ ► which came weeks late, very recently, right away. I got into OpenAI chat right away, and
01:55:26 ◼ ► not by pulling strings like I contacted the—I'm John Gruber at Daring Fireball—I just signed
01:55:31 ◼ ► up on the regular waiting list and waited, but I got in early. BARD, though, I only got
01:55:40 ◼ ► know that Bard is a totally independent LLM, or large language, yeah, LLM inside Google.
01:55:49 ◼ ► But it's shocking to me, not shocking, surprising, but not shocking how similar the answers are
01:55:55 ◼ ► to ChatGPT, right? It's an entirely different model, massive amounts of years of academic
01:56:04 ◼ ► AI study and inordinate amounts of aggregate computing power to compile the model, like
01:56:17 ◼ ► the thing they built for OpenAI with gazillion NVIDIA video cards in a cluster together to
01:56:25 ◼ ► do this. Massive amounts of computing power thrown at it, and then you get the same answers
01:56:31 ◼ ► from the same questions. It's very, very similar. And I guess the explanation is that the theory
01:56:38 ◼ ► of how large language models work mean that if you train them on the same corpus and the corpus for
01:56:45 ◼ ► all these things is the internet, right, and the internet's the internet for everybody, then of
01:56:51 ◼ ► course you're going to get similar results if it's—I don't know. I don't know how surprised we
01:57:02 ◼ ► broke it down to the simplest thing, if you said like Microsoft and Google have independently
01:57:09 ◼ ► come up with algorithms that rank the prevalence of letters and words, right? And they would come
01:57:17 ◼ ► out to be the same. And I guess maybe that does explain it at a bigger level, but I agree it's
01:57:24 ◼ ► kind of weird, especially. But that sort of lends itself to the argument that these things
01:57:35 ◼ ► aren't actually smart. The comeback to people like you and I kind of feeling a little bit
01:57:41 ◼ ► spooked out and we need to control these things. Some people have said that these things aren't
01:57:50 ◼ ► smart, they're just kind of like a dolled-up Google result, right? And when I see things
01:58:00 ◼ ► like the same kind of response from two technologically independent companies, or I see things like
01:58:20 ◼ ► And then you ask it to write another poem or another song, and it's like, "Wait, you're
01:58:34 ◼ ► this amazing song, and then you ask them to play something else, and they play a completely
01:59:12 ◼ ► Yeah. I also think the thing—and again, I don't know that society is ready for it—is that
01:59:20 ◼ ► it touches on a sensitive subject, but it's the nature of our existence and our intelligence. And
01:59:31 ◼ ► the truth is probably, in my opinion, that our idea and concept of consciousness and personality,
01:59:47 ◼ ► series of parlor tricks. Right? And so, the argument on the one end that, "Oh, these chats
01:59:56 ◼ ► are just a parlor trick," and they're very simple, and right now you can confuse them by asking them
02:00:00 ◼ ► how many letters are in the word color, and it says it's a six-letter word, and it's not—or
02:00:06 ◼ ► I guess it is in England, but not in the US. See, it's not intelligence, but it's like,
02:00:12 ◼ ► ask chat GPT for the same question and you get the right answer. I just asked Bard right here while
02:00:17 ◼ ► you were talking, and Bard knows that color has five letters. And as these parlor tricks get
02:00:24 ◼ ► better, you can unfold, unpeel the onion and see its parlor tricks all the way down, but if the end
02:00:32 ◼ ► result is indistinguishable from intelligence, isn't it intelligence? And the truth is,
02:00:37 ◼ ► I think through evolution, what we've got is just a very unbelievably beautiful and complex
02:00:44 ◼ ► machine in our brains, but it is just a series of parlor tricks, right? I mean, I mentioned
02:00:49 ◼ ► vision problems before. The way our human vision works is really a series of very fascinating
02:01:00 ◼ ► Jared: Right. I think what I would say is the parlor tricks aspect is the ability of a person
02:01:10 ◼ ► or computer to regurgitate something that is structured in a way that appears intelligent.
02:03:17 ◼ ► to prevent humans from keeping it from making more paper clips out of every single atom
02:03:30 ◼ ► Squarespace is the all-in-one platform for building your presence online, and they handle
02:03:38 ◼ ► everything you need to have your own website, from domain name registration, which is the
02:03:42 ◼ ► The first thing you need to decide to picking templates, to adding features, to customizing
02:03:48 ◼ ► those features, to updating your website on a regular basis with something like blog posts
02:03:54 ◼ ► or if you've got a catalog, if you're creating an online store to sell stuff to keep the
02:04:01 ◼ ► Everything you need, analytics, see who's coming to your website from where, which parts
02:04:06 ◼ ► of the website are popular, which parts aren't, where people are going on your website once
02:04:12 ◼ ► it in a very, very, very approachable analytic interface that is so much better. So I mean,
02:04:19 ◼ ► like, the 1000 times better. Like the difference between reading a novel from your favorite novelist
02:04:28 ◼ ► to reading the phone book difference between like, say, Google Analytics interface in terms
02:04:34 ◼ ► of complexity, awesome analytics interface at Squarespace, everything you need. If you need a
02:04:40 ◼ ► website. Try them out 30 days free. No watermarks on the website. Everything you need to do,
02:04:47 ◼ ► no credit card required. Just go to squarespace.com/talkshow to start. "Talkshow" is the code that tells
02:05:01 ◼ ► as their nerd in their circle to help them get started with a website, send them to Squarespace.
02:05:07 ◼ ► could do it themselves. That's how low technical need it is to get started on Squarespace building
02:05:13 ◼ ► a website. So my thanks to them for their continued support of the show. Once again, the web, the URL
02:05:18 ◼ ► is squarespace.com/talkshow. Gets you a free trial, 30 days, and when you're ready to launch
02:05:25 ◼ ► and start paying the same offer code, talk show, without the "the," just talk show, gets you 10%
02:05:31 ◼ ► off your first purchase. Pre-pay for up to a year, get 10% off. My thanks to Squarespace.
02:05:36 ◼ ► Anything else on this front? Have you played with GTP4 at all? I guess you did because you
02:05:42 ◼ ► said you've been using your one a day at Po. Yes, I use one a day at Po and I'm a little
02:05:54 ◼ ► They're very cagey about it, right? And I guess that they talk about GTP3.5. I don't know what
02:06:02 ◼ ► the point. It's like version numbers are always sort of some programmer's idea of a benchmark
02:06:07 ◼ ► or a milestone. It seems to me like Bing Chat is too fast to beat GPT-4, but maybe that's just a
02:06:15 ◼ ► function of Azure's incredible cloud infrastructure compared to OpenAI. I know our mutual friend,
02:06:23 ◼ ► Ben Thompson, has speculated maybe the future of OpenAI is to no longer run their own thing
02:06:33 ◼ ► This stuff is crazy, crazy expensive on the back end. And GPT-4 in particular sounds like,
02:06:40 ◼ ► oh, you go from GPT-3 to 3.5 to version 4, and of course it gets a little better. But version 4
02:06:46 ◼ ► is crazy more expensive. So if you're running a service and you're a paying customer with an API
02:06:54 ◼ ► token to open AI, it's like 25 times more expensive per query to use GPT-4 than GPT-3.5.
02:07:05 ◼ ► Maybe more. 25x might be off on the low end. So there's a reason why so many things with
02:07:11 ◼ ► GPT integration are all on 3.5 because the 4 is so much more expensive. But even though
02:07:23 ◼ ► Honestly, it's worth it because these responses are so interesting. But it's another one
02:07:28 ◼ ► of those things that harks back 30 years to like when we first got the web and you would
02:07:33 ◼ ► type a query and then it would just feel totally natural to wait a minute or 30 seconds to
02:07:52 ◼ ► shutting down because of Amazon layoffs. They've owned them since like 2007, I think, and DP Review
02:07:59 ◼ ► was around since 1998. And I remember when they were new, because I remember being intrigued.
02:08:04 ◼ ► And that's another one of those things where like the first few years of digital cameras,
02:08:07 ◼ ► the imagery was terrible, just terrible compared to like $180 film camera you could go to any store
02:08:14 ◼ ► and buy, and buy just generic Kodak 100 ISO film. You'd get such better imagery off the
02:08:21 ◼ ► cheapest camera you could buy compared to the $2,000 digital camera in 1998. But the future was
02:08:29 ◼ ► obvious, right? So sad to see DPReview go. But the other 90s era acquisition Amazon made, they
02:08:36 ◼ ► bought IMDb back in the 90s, I think. I think they've owned them since then. And IMDb is still
02:08:42 ◼ ► thriving, right? And it's still a great source for like, who's in that movie, right? Or who directed
02:08:48 ◼ ► such and such. It's great. But I remember using IMDb before the web. I was taking film classes
02:08:54 ◼ ► at Drexel. And it was like the way these classes, I took like a Hitchcock class, a Westerns class.
02:09:01 ◼ ► Every week we'd watch them, like on Monday, we'd watch a movie. The whole movie, it was like a
02:09:07 ◼ ► three-hour class where we'd have like an hour of lecture and then we'd watch a two-hour feature
02:09:11 ◼ ► film. And then on Friday, we'd have to hand in a paper about the film that we watched. And we'd
02:09:17 ◼ ► have a class discussion about our papers. And it was this huge help when writing a paper about a
02:09:24 ◼ ► movie to consult with IMDb to get the cast, right? And if you wanted to talk about the screenwriter,
02:09:31 ◼ ► you just give it. But the interface to IMDb in like the mid-90s, like I don't know, this is
02:09:36 ◼ ► probably like 1994 or so, it was email. You would email, there was a magic address at imdb.com,
02:09:43 ◼ ► and then the subject would be the string you were searching for, like the birds by Alfred Hitchcock.
02:09:51 ◼ ► And then you'd email them, and then two or three minutes later, you would get an email back,
02:10:16 ◼ ► chat GPT force feels like. It's like you type your thing, it goes off, and then you get this
02:10:23 ◼ ► amazing answer. What I think is fascinating is all of us alive today, except for a very,
02:10:40 ◼ ► would have found GPT 3.5 to be beyond our wildest expectations six months ago or whatever, right?
02:10:48 ◼ ► And now we're like, "Oh, GPT 3.5, that's old and busted." That's junk now. It's just the nature
02:10:55 ◼ ► of technology, but it's kind of funny to me that in this context, how fast that has happened.
02:11:09 ◼ ► But in this context, it's like not only is the old GPT "junk," but it's junk while still being
02:11:40 ◼ ► do you know about John Gruber?" And the 3.5 answer is, "John Gruber is a writer, blogger,
02:11:48 ◼ ► and related technologies. He is also the co-host of the podcast, The Talk Show with John Gruber."
02:11:58 ◼ ► But also, but it's half wrong because then it wasn't The Talk Show with John Gruber, right?
02:12:02 ◼ ► But still, overall, you got to give that a thumbs up as a bio for me. Then my follow-up question in
02:12:08 ◼ ► the same chat, "What's his favorite baseball team?" And the answer is, "I do not know for certain what
02:12:14 ◼ ► John Gruber's favorite baseball team is, as I do not have access to personal information about
02:12:19 ◼ ► him. However, as far as I'm aware, he has not publicly disclosed any favorite baseball team."
02:12:24 ◼ ► Well, that is wrong. Now, GPT-4, what do you know about John Gruber? John Gruber is an American
02:12:31 ◼ ► writer, programmer, and web designer best known for his blog, Daring Fireball, which he founded
02:12:36 ◼ ► in 2002. Daring Fireball focuses primarily on topics related to Apple Link and its products
02:12:41 ◼ ► and software and the tech industry in general. Gruber is also the inventor of the Markdown text
02:12:46 ◼ ► formatting syntax, a lightweight markup language designed to simplify the process of writing web
02:12:51 ◼ ► content. Markdown has become widely popular and is now used extensively for documentation,
02:12:56 ◼ ► note-taking, and more. In addition to his blog, Gruber hosts a podcast called The Talk Show where
02:13:00 ◼ ► he discusses technology design and related topics with various guests. He has an influential presence
02:13:06 ◼ ► in the tech community, especially among Apple enthusiasts. Holy fucking shit. Is that a good
02:13:13 ◼ ► biography of me? I don't know. I don't know that I can improve it. And I'm supposed to be a writer,
02:13:19 ◼ ► right? I mean, in the right facts in the right order. I mean, holy shit. Really? Now what's his
02:13:28 ◼ ► favorite baseball team. John Gruber's favorite baseball team is the Philadelphia Phillies.
02:13:32 ◼ ► He has met, he has met, he has mentioned his support for the team in various online platforms
02:13:37 ◼ ► and has discussed baseball topics on his blog during Fireball and his podcast, The Talk Show.
02:13:41 ◼ ► The Phillies are a major league baseball team based in Philadelphia, Pennsylvania. So they are
02:13:46 ◼ ► my second favorite team. It's fascinating. But they're your, they're your second favorite team,
02:14:04 ◼ ► Right, right. Exactly. It's like if you have to pick a backup team, then I guess you'll go with it.
02:14:12 ◼ ► I don't know where they got it. And my first thought was maybe because when the Phillies
02:14:15 ◼ ► were in the World Series just a few months ago, I did express that I was rooting for them at the
02:14:19 ◼ ► Houston Astros, but I realize that has to be wrong because infamously or famously, however you want
02:14:24 ◼ ► to prefer, even chat GPT-4, the data corpus cutoff is 2021, so that can't be. I don't know where
02:14:31 ◼ ► this came from. It must be some kind—I think it's probably an educated guess because it knows I do
02:14:36 ◼ ► live in Philadelphia, so I think it's one of those things where they're making up facts based on a
02:15:39 ◼ ► It is noticeably slower. Like even he said, I've been chatting with him. He keeps it on 3.5 and
02:15:45 ◼ ► it's not because of the cost because it's still at a—it's 25 times more expensive, but it's still
02:15:50 ◼ ► like a fraction of a penny. It's just almost a penny as opposed to a fraction of a penny.
02:15:55 ◼ ► It's just that when it goes wider, he'll have to charge for it. His name, I'm going to—sorry,
02:16:11 ◼ ► I'm sorry, I'm gonna guess it's well PD is a lot more. Yeah. But anyway, it's a very fun app. Very simple
02:16:22 ◼ ► But I love it gets to your your and my love for natural apps native apps, right? It's I need to check it out
02:16:31 ◼ ► Yeah, and also, frankly, it has a better interface than Po, because Po is clearly like a sort
02:16:36 ◼ ► of, even on mobile, is sort of a web interface, because I guess it's the same interface on
02:16:58 ◼ ► I'm breaking a friend DNA friend da that anything else you wanted to talk about before we wrap up
02:17:04 ◼ ► Daniel I don't think so this has been a fun fun time oh I did good stuff I knew you'd be intrigued
02:17:11 ◼ ► by it let's let's give a shout out to to pimp all the stuff that we can you've got your your
02:17:16 ◼ ► your regular podcast with you as mentioned earlier you are our mutual friend manton reese which is
02:17:36 ◼ ► So I normally would give my Twitter handle right now, and I'm going to give my mastodon.social
02:18:18 ◼ ► As we've discussed before, it took me 20 years to get the hyphen out of that domain name.
02:18:54 ◼ ► So, yeah, that's a good segue to Fast Scripts is another app that Jon sometimes gives me
02:18:59 ◼ ► But yeah, the latest version of Fast Scripts, I had to check in with Jon about some changes
02:19:23 ◼ ► My uncanny ability to craft regular expressions is useless now because these ChatGPT things
02:20:59 ◼ ► poe tic-tac-toe. And I was going to beat it and I was feeling very happy about the fact
02:21:05 ◼ ► that you're so stupid you do know how to play tic-tac-toe but you actually can't beat this
02:21:09 ◼ ► simple game. And as I was about to make the winning move it told me the game was already
02:22:10 ◼ ► then they do the dumbest thing in the world and you're like, "Oh yeah, three-year-old."
02:22:15 ◼ ► Anyway, Daniel, good to talk to you. Thank you. And let me just give one quick shout-out
02:22:19 ◼ ► to our sponsors, our good friends at Collide, where if you're into Okta, you can get your